diff --git a/grain_size_tools/example_notebooks/getting_started.ipynb b/grain_size_tools/example_notebooks/getting_started.ipynb index d37e728..1899801 100644 --- a/grain_size_tools/example_notebooks/getting_started.ipynb +++ b/grain_size_tools/example_notebooks/getting_started.ipynb @@ -19,26 +19,10 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ - "module plot imported\n", - "module averages imported\n", - "module stereology imported\n", - "module piezometers imported\n", - "module template imported\n", - "\n", - "======================================================================================\n", - "Welcome to GrainSizeTools script\n", - "======================================================================================\n", - "A free open-source cross-platform script to visualize and characterize grain size\n", - "population and estimate differential stress via paleopizometers.\n", - "\n", - "Version: v3.0RC0 (2020-04-23)\n", - "Documentation: https://marcoalopez.github.io/GrainSizeTools/\n", - "\n", - "Type get.functions_list() to get a list of the main methods\n", - "\n" + "module plot imported\nmodule averages imported\nmodule stereology imported\nmodule piezometers imported\nmodule template imported\n\n======================================================================================\nWelcome to GrainSizeTools script\n======================================================================================\nA free open-source cross-platform script to visualize and characterize grain size\npopulation and estimate differential stress via paleopizometers.\n\nVersion: v3.0.2 (2020-12-30)\nDocumentation: https://marcoalopez.github.io/GrainSizeTools/\n\nType get.functions_list() to get a list of the main methods\n\n" ] } ], @@ -63,33 +47,10 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ - "\n", - "======================================================================================\n", - "List of main functions\n", - "======================================================================================\n", - "summarize -> get the properties of the data population\n", - "conf_interval -> estimate a robust confidence interval using the t-distribution\n", - "calc_diffstress -> estimate diff. stress from grain size using piezometers\n", - "\n", - "plot.distribution -> visualize the distribution of grain sizes and locate the averages\n", - "plot.qq_plot -> test the lognormality of the dataset (q-q plot + Shapiro-Wilk test)\n", - "plot.area_weighted -> visualize the area-weighed distribution of grain sizes\n", - "plot.normalized -> visualize a normalized distribution of grain sizes\n", - "\n", - "stereology.Saltykov -> approximate the actual grain size distribution via the Saltykov method\n", - "stereology.calc_shape -> approximate the lognormal shape of the actual distribution\n", - "======================================================================================\n", - "\n", - "You can get more information about the methods using the following ways:\n", - " (1) Typing ? or ?? after the function name, e.g. ?summarize\n", - " (2) Typing help plus the name of the function, e.g. help(summarize)\n", - " (3) In the Spyder IDE by writing the name of the function and clicking Ctrl + I\n", - " (4) In Jupyter lab/notebook by enabling the \"Show contextual help\", the info\n", - " will pop up as soon as you write the name of the function.\n", - "\n" + "\n======================================================================================\nList of main functions\n======================================================================================\nsummarize -> get the properties of the data population\nconf_interval -> estimate a robust confidence interval using the t-distribution\ncalc_diffstress -> estimate diff. stress from grain size using piezometers\n\nplot.distribution -> visualize the distribution of grain sizes and locate the averages\nplot.qq_plot -> test the lognormality of the dataset (q-q plot + Shapiro-Wilk test)\nplot.area_weighted -> visualize the area-weighed distribution of grain sizes\nplot.normalized -> visualize a normalized distribution of grain sizes\n\nstereology.Saltykov -> approximate the actual grain size distribution via the Saltykov method\nstereology.calc_shape -> approximate the lognormal shape of the actual distribution\n======================================================================================\n\nYou can get more information about the methods using the following ways:\n (1) Typing ? or ?? after the function name, e.g. ?summarize\n (2) Typing help plus the name of the function, e.g. help(summarize)\n (3) In the Spyder IDE by writing the name of the function and clicking Ctrl + I\n (4) In Jupyter lab/notebook by enabling the \"Show contextual help\", the info\n will pop up as soon as you write the name of the function.\n\n" ] } ], @@ -121,41 +82,39 @@ "metadata": {}, "outputs": [ { - "data": { - "text/plain": [ - "\u001b[1;31mSignature:\u001b[0m \u001b[0mconf_interval\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mconfidence\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0.95\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;31mDocstring:\u001b[0m\n", - "Estimate the confidence interval using the t-distribution with n-1\n", - "degrees of freedom t(n-1). This is the way to go when sample size is\n", - "small (n < 30) and the standard deviation cannot be estimated accurately.\n", - "For large datasets, the t-distribution approaches the normal distribution.\n", - "\n", - "Parameters\n", - "----------\n", - "data : array-like\n", - " the dataset\n", - "\n", - "confidence : float between 0 and 1, optional\n", - " the confidence interval, default = 0.95\n", - "\n", - "Assumptions\n", - "-----------\n", - "the data follows a normal or symmetric distrubution (when sample size\n", - "is large)\n", - "\n", - "call_function(s)\n", - "----------------\n", - "Scipy's t.interval\n", - "\n", - "Returns\n", - "-------\n", - "the arithmetic mean, the error, and the limits of the confidence interval\n", - "\u001b[1;31mFile:\u001b[0m c:\\users\\marco\\documents\\github\\grainsizetools\\grain_size_tools\\grainsizetools_script.py\n", - "\u001b[1;31mType:\u001b[0m function\n" - ] - }, - "metadata": {}, - "output_type": "display_data" + "output_type": "stream", + "text": [ + "\u001b[1;31mSignature:\u001b[0m \u001b[0mconf_interval\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mconfidence\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0.95\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;31mDocstring:\u001b[0m\n", + "Estimate the confidence interval using the t-distribution with n-1\n", + "degrees of freedom t(n-1). This is the way to go when sample size is\n", + "small (n < 30) and the standard deviation cannot be estimated accurately.\n", + "For large datasets, the t-distribution approaches the normal distribution.\n", + "\n", + "Parameters\n", + "----------\n", + "data : array-like\n", + " the dataset\n", + "\n", + "confidence : float between 0 and 1, optional\n", + " the confidence interval, default = 0.95\n", + "\n", + "Assumptions\n", + "-----------\n", + "the data follows a normal or symmetric distrubution (when sample size\n", + "is large)\n", + "\n", + "call_function(s)\n", + "----------------\n", + "Scipy's t.interval\n", + "\n", + "Returns\n", + "-------\n", + "the arithmetic mean, the error, and the limits of the confidence interval\n", + "\u001b[1;31mFile:\u001b[0m c:\\users\\marco\\documents\\github\\grainsizetools\\grain_size_tools\\grainsizetools_script.py\n", + "\u001b[1;31mType:\u001b[0m function\n" + ], + "name": "stdout" } ], "source": [ @@ -199,199 +158,8 @@ "metadata": {}, "outputs": [ { + "output_type": "execute_result", "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
AreaCirc.FeretFeretXFeretYFeretAngleMinFeretARRoundSolidity
01157.250.68018.0621535.00.5131.63413.5001.1010.9080.937
122059.750.77162.097753.516.5165.06946.6971.3140.7610.972
231961.500.84257.871727.065.071.87846.9231.1390.8780.972
345428.500.709114.6571494.583.519.62063.4491.8960.5280.947
45374.000.69929.2622328.034.033.14716.0001.5150.6600.970
....................................
26562657452.500.78928.5041368.01565.5127.87522.5001.2350.8100.960
265726581081.250.75647.9091349.51569.5108.24631.3631.4460.6920.960
26582659513.500.72032.9621373.01586.0112.28620.4961.4930.6700.953
26592660277.750.62729.4361316.01601.5159.10217.0021.7270.5790.920
26602661725.000.74839.4371335.51615.5129.34128.0251.3510.7400.960
\n", - "

2661 rows × 11 columns

\n", - "
" - ], "text/plain": [ " Area Circ. Feret FeretX FeretY FeretAngle MinFeret \\\n", "0 1 157.25 0.680 18.062 1535.0 0.5 131.634 13.500 \n", @@ -420,11 +188,11 @@ "2660 1.351 0.740 0.960 \n", "\n", "[2661 rows x 11 columns]" - ] + ], + "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
AreaCirc.FeretFeretXFeretYFeretAngleMinFeretARRoundSolidity
01157.250.68018.0621535.00.5131.63413.5001.1010.9080.937
122059.750.77162.097753.516.5165.06946.6971.3140.7610.972
231961.500.84257.871727.065.071.87846.9231.1390.8780.972
345428.500.709114.6571494.583.519.62063.4491.8960.5280.947
45374.000.69929.2622328.034.033.14716.0001.5150.6600.970
....................................
26562657452.500.78928.5041368.01565.5127.87522.5001.2350.8100.960
265726581081.250.75647.9091349.51569.5108.24631.3631.4460.6920.960
26582659513.500.72032.9621373.01586.0112.28620.4961.4930.6700.953
26592660277.750.62729.4361316.01601.5159.10217.0021.7270.5790.920
26602661725.000.74839.4371335.51615.5129.34128.0251.3510.7400.960
\n

2661 rows × 11 columns

\n
" }, - "execution_count": 4, "metadata": {}, - "output_type": "execute_result" + "execution_count": 4 } ], "source": [ @@ -456,14 +224,14 @@ "metadata": {}, "outputs": [ { + "output_type": "execute_result", "data": { "text/plain": [ "pandas.core.frame.DataFrame" ] }, - "execution_count": 5, "metadata": {}, - "output_type": "execute_result" + "execution_count": 5 } ], "source": [ @@ -522,114 +290,8 @@ "metadata": {}, "outputs": [ { + "output_type": "execute_result", "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
AreaCirc.FeretFeretXFeretYFeretAngleMinFeretARRoundSolidity
01157.250.68018.0621535.00.5131.63413.5001.1010.9080.937
122059.750.77162.097753.516.5165.06946.6971.3140.7610.972
231961.500.84257.871727.065.071.87846.9231.1390.8780.972
345428.500.709114.6571494.583.519.62063.4491.8960.5280.947
45374.000.69929.2622328.034.033.14716.0001.5150.6600.970
\n", - "
" - ], "text/plain": [ " Area Circ. Feret FeretX FeretY FeretAngle MinFeret AR \\\n", "0 1 157.25 0.680 18.062 1535.0 0.5 131.634 13.500 1.101 \n", @@ -644,11 +306,11 @@ "2 0.878 0.972 \n", "3 0.528 0.947 \n", "4 0.660 0.970 " - ] + ], + "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
AreaCirc.FeretFeretXFeretYFeretAngleMinFeretARRoundSolidity
01157.250.68018.0621535.00.5131.63413.5001.1010.9080.937
122059.750.77162.097753.516.5165.06946.6971.3140.7610.972
231961.500.84257.871727.065.071.87846.9231.1390.8780.972
345428.500.709114.6571494.583.519.62063.4491.8960.5280.947
45374.000.69929.2622328.034.033.14716.0001.5150.6600.970
\n
" }, - "execution_count": 6, "metadata": {}, - "output_type": "execute_result" + "execution_count": 6 } ], "source": [ @@ -668,6 +330,7 @@ "metadata": {}, "outputs": [ { + "output_type": "execute_result", "data": { "text/plain": [ "0 314.5\n", @@ -684,9 +347,8 @@ "Name: Area, Length: 2661, dtype: float64" ] }, - "execution_count": 7, "metadata": {}, - "output_type": "execute_result" + "execution_count": 7 } ], "source": [ @@ -707,82 +369,8 @@ "metadata": {}, "outputs": [ { + "output_type": "execute_result", "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
AreaCirc.FeretFeretXFeretYFeretAngleMinFeretARRoundSolidity
0157.250.68018.0621535.00.5131.63413.5001.1010.9080.937
12059.750.77162.097753.516.5165.06946.6971.3140.7610.972
21961.500.84257.871727.065.071.87846.9231.1390.8780.972
\n", - "
" - ], "text/plain": [ " Area Circ. Feret FeretX FeretY FeretAngle MinFeret AR Round \\\n", "0 157.25 0.680 18.062 1535.0 0.5 131.634 13.500 1.101 0.908 \n", @@ -793,11 +381,11 @@ "0 0.937 \n", "1 0.972 \n", "2 0.972 " - ] + ], + "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
AreaCirc.FeretFeretXFeretYFeretAngleMinFeretARRoundSolidity
0157.250.68018.0621535.00.5131.63413.5001.1010.9080.937
12059.750.77162.097753.516.5165.06946.6971.3140.7610.972
21961.500.84257.871727.065.071.87846.9231.1390.8780.972
\n
" }, - "execution_count": 8, "metadata": {}, - "output_type": "execute_result" + "execution_count": 8 } ], "source": [ @@ -812,84 +400,18 @@ "metadata": {}, "outputs": [ { + "output_type": "execute_result", "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
AreaCirc.FeretFeretAngleMinFeretARRoundSolidity
0157.250.68018.062131.63413.5001.1010.9080.937
12059.750.77162.097165.06946.6971.3140.7610.972
21961.500.84257.87171.87846.9231.1390.8780.972
\n", - "
" - ], "text/plain": [ " Area Circ. Feret FeretAngle MinFeret AR Round Solidity\n", "0 157.25 0.680 18.062 131.634 13.500 1.101 0.908 0.937\n", "1 2059.75 0.771 62.097 165.069 46.697 1.314 0.761 0.972\n", "2 1961.50 0.842 57.871 71.878 46.923 1.139 0.878 0.972" - ] + ], + "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
AreaCirc.FeretFeretAngleMinFeretARRoundSolidity
0157.250.68018.062131.63413.5001.1010.9080.937
12059.750.77162.097165.06946.6971.3140.7610.972
21961.500.84257.87171.87846.9231.1390.8780.972
\n
" }, - "execution_count": 9, "metadata": {}, - "output_type": "execute_result" + "execution_count": 9 } ], "source": [ @@ -917,102 +439,8 @@ "metadata": {}, "outputs": [ { + "output_type": "execute_result", "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
AreaCirc.FeretFeretAngleMinFeretARRoundSoliditydiameters
0157.250.68018.062131.63413.5001.1010.9080.93714.149803
12059.750.77162.097165.06946.6971.3140.7610.97251.210889
21961.500.84257.87171.87846.9231.1390.8780.97249.974587
35428.500.709114.65719.62063.4491.8960.5280.94783.137121
4374.000.69929.26233.14716.0001.5150.6600.97021.821815
\n", - "
" - ], "text/plain": [ " Area Circ. Feret FeretAngle MinFeret AR Round Solidity \\\n", "0 157.25 0.680 18.062 131.634 13.500 1.101 0.908 0.937 \n", @@ -1027,11 +455,11 @@ "2 49.974587 \n", "3 83.137121 \n", "4 21.821815 " - ] + ], + "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
AreaCirc.FeretFeretAngleMinFeretARRoundSoliditydiameters
0157.250.68018.062131.63413.5001.1010.9080.93714.149803
12059.750.77162.097165.06946.6971.3140.7610.97251.210889
21961.500.84257.87171.87846.9231.1390.8780.97249.974587
35428.500.709114.65719.62063.4491.8960.5280.94783.137121
4374.000.69929.26233.14716.0001.5150.6600.97021.821815
\n
" }, - "execution_count": 10, "metadata": {}, - "output_type": "execute_result" + "execution_count": 10 } ], "source": [ @@ -1084,6 +512,7 @@ "metadata": {}, "outputs": [ { + "output_type": "execute_result", "data": { "text/plain": [ "Area 1213.823750\n", @@ -1098,9 +527,8 @@ "dtype: float64" ] }, - "execution_count": 11, "metadata": {}, - "output_type": "execute_result" + "execution_count": 11 } ], "source": [ @@ -1114,138 +542,8 @@ "metadata": {}, "outputs": [ { + "output_type": "execute_result", "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
AreaCirc.FeretFeretAngleMinFeretARRoundSoliditydiameters
count2661.0000002661.0000002661.0000002661.0000002661.0000002661.0000002661.0000002661.0000002661.000000
mean1213.8237500.73023344.80874990.62231331.0163301.4514590.7192530.94379534.785694
std1331.4623280.06944121.76406253.57046617.0794550.3373580.1367510.02759018.318569
min8.0000000.3770004.3010001.0710002.5000001.0040000.2360000.7640003.191538
25%346.5000000.69100029.10800041.56600018.0630001.2110000.6260000.93200021.004226
50%780.7500000.74200041.40400087.27400028.3060001.3680000.7310000.95000031.529062
75%1589.5000000.78000056.447000141.74600040.7910001.5970000.8260000.96300044.986823
max19259.7500000.873000177.229000179.576000146.3630004.2440000.9960000.985000156.595898
\n", - "
" - ], "text/plain": [ " Area Circ. Feret FeretAngle MinFeret \\\n", "count 2661.000000 2661.000000 2661.000000 2661.000000 2661.000000 \n", @@ -1266,11 +564,11 @@ "50% 1.368000 0.731000 0.950000 31.529062 \n", "75% 1.597000 0.826000 0.963000 44.986823 \n", "max 4.244000 0.996000 0.985000 156.595898 " - ] + ], + "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
AreaCirc.FeretFeretAngleMinFeretARRoundSoliditydiameters
count2661.0000002661.0000002661.0000002661.0000002661.0000002661.0000002661.0000002661.0000002661.000000
mean1213.8237500.73023344.80874990.62231331.0163301.4514590.7192530.94379534.785694
std1331.4623280.06944121.76406253.57046617.0794550.3373580.1367510.02759018.318569
min8.0000000.3770004.3010001.0710002.5000001.0040000.2360000.7640003.191538
25%346.5000000.69100029.10800041.56600018.0630001.2110000.6260000.93200021.004226
50%780.7500000.74200041.40400087.27400028.3060001.3680000.7310000.95000031.529062
75%1589.5000000.78000056.447000141.74600040.7910001.5970000.8260000.96300044.986823
max19259.7500000.873000177.229000179.576000146.3630004.2440000.9960000.985000156.595898
\n
" }, - "execution_count": 12, "metadata": {}, - "output_type": "execute_result" + "execution_count": 12 } ], "source": [ @@ -1284,24 +582,23 @@ "metadata": {}, "outputs": [ { + "output_type": "execute_result", "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 13, "metadata": {}, - "output_type": "execute_result" + "execution_count": 13 }, { + "output_type": "display_data", "data": { - "image/png": "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\n", - "text/plain": [ - "
" - ] + "text/plain": "
", + "image/svg+xml": "\r\n\r\n\r\n\r\n \r\n \r\n \r\n \r\n 2020-12-31T14:09:49.378057\r\n image/svg+xml\r\n \r\n \r\n Matplotlib v3.3.2, https://matplotlib.org/\r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n\r\n", + "image/png": "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\n" }, - "metadata": {}, - "output_type": "display_data" + "metadata": {} } ], "source": [ @@ -1332,9 +629,9 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.7" + "version": "3.7.9-final" } }, "nbformat": 4, "nbformat_minor": 4 -} +} \ No newline at end of file diff --git a/grain_size_tools/example_notebooks/grain_size_description.ipynb b/grain_size_tools/example_notebooks/grain_size_description.ipynb index e44d9d2..03c7dab 100644 --- a/grain_size_tools/example_notebooks/grain_size_description.ipynb +++ b/grain_size_tools/example_notebooks/grain_size_description.ipynb @@ -15,26 +15,10 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ - "module plot imported\n", - "module averages imported\n", - "module stereology imported\n", - "module piezometers imported\n", - "module template imported\n", - "\n", - "======================================================================================\n", - "Welcome to GrainSizeTools script\n", - "======================================================================================\n", - "A free open-source cross-platform script to visualize and characterize grain size\n", - "population and estimate differential stress via paleopizometers.\n", - "\n", - "Version: v3.0RC0 (2020-04-23)\n", - "Documentation: https://marcoalopez.github.io/GrainSizeTools/\n", - "\n", - "Type get.functions_list() to get a list of the main methods\n", - "\n" + "module plot imported\nmodule averages imported\nmodule stereology imported\nmodule piezometers imported\nmodule template imported\n\n======================================================================================\nWelcome to GrainSizeTools script\n======================================================================================\nA free open-source cross-platform script to visualize and characterize grain size\npopulation and estimate differential stress via paleopizometers.\n\nVersion: v3.0.2 (2020-12-30)\nDocumentation: https://marcoalopez.github.io/GrainSizeTools/\n\nType get.functions_list() to get a list of the main methods\n\n" ] } ], @@ -49,120 +33,8 @@ "metadata": {}, "outputs": [ { + "output_type": "execute_result", "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
AreaCirc.FeretFeretXFeretYFeretAngleMinFeretARRoundSoliditydiameters
01157.250.68018.0621535.00.5131.63413.5001.1010.9080.93714.149803
122059.750.77162.097753.516.5165.06946.6971.3140.7610.97251.210889
231961.500.84257.871727.065.071.87846.9231.1390.8780.97249.974587
345428.500.709114.6571494.583.519.62063.4491.8960.5280.94783.137121
45374.000.69929.2622328.034.033.14716.0001.5150.6600.97021.821815
\n", - "
" - ], "text/plain": [ " Area Circ. Feret FeretX FeretY FeretAngle MinFeret AR \\\n", "0 1 157.25 0.680 18.062 1535.0 0.5 131.634 13.500 1.101 \n", @@ -177,11 +49,11 @@ "2 0.878 0.972 49.974587 \n", "3 0.528 0.947 83.137121 \n", "4 0.660 0.970 21.821815 " - ] + ], + "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
AreaCirc.FeretFeretXFeretYFeretAngleMinFeretARRoundSoliditydiameters
01157.250.68018.0621535.00.5131.63413.5001.1010.9080.93714.149803
122059.750.77162.097753.516.5165.06946.6971.3140.7610.97251.210889
231961.500.84257.871727.065.071.87846.9231.1390.8780.97249.974587
345428.500.709114.6571494.583.519.62063.4491.8960.5280.94783.137121
45374.000.69929.2622328.034.033.14716.0001.5150.6600.97021.821815
\n
" }, - "execution_count": 2, "metadata": {}, - "output_type": "execute_result" + "execution_count": 2 } ], "source": [ @@ -200,8 +72,8 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ "sample size = 500\n" ] @@ -231,41 +103,10 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ - " \n", - "============================================================================\n", - "CENTRAL TENDENCY ESTIMATORS\n", - "============================================================================\n", - "Arithmetic mean = 22.13 microns\n", - "Confidence intervals at 95.0 %\n", - "mCox method: 21.35 - 22.98 (-3.5%, +3.8%), length = 1.623\n", - "============================================================================\n", - "Geometric mean = 20.44 microns\n", - "Confidence interval at 95.0 %\n", - "CLT method: 19.73 - 21.17 (-3.5%, +3.6%), length = 1.441\n", - "============================================================================\n", - "Median = 20.32 microns\n", - "Confidence interval at 95.0 %\n", - "robust method: 19.33 - 21.42 (-4.9%, +5.4%), length = 2.096\n", - "============================================================================\n", - "Mode (KDE-based) = 17.66 microns\n", - "Maximum precision set to 0.1\n", - "KDE bandwidth = 2.78 (silverman rule)\n", - " \n", - "============================================================================\n", - "DISTRIBUTION FEATURES\n", - "============================================================================\n", - "Sample size (n) = 500\n", - "Standard deviation = 9.07 (1-sigma)\n", - "Interquartile range (IQR) = 11.44\n", - "Lognormal shape (Multiplicative Standard Deviation) = 1.49\n", - "============================================================================\n", - "Shapiro-Wilk test warnings:\n", - "Data is not normally distributed!\n", - "Normality test: 0.88, 0.00 (test statistic, p-value)\n", - "============================================================================\n" + " \n============================================================================\nCENTRAL TENDENCY ESTIMATORS\n============================================================================\nArithmetic mean = 22.13 microns\nConfidence intervals at 95.0 %\nmCox method: 21.35 - 22.98 (-3.5%, +3.8%), length = 1.623\n============================================================================\nGeometric mean = 20.44 microns\nConfidence interval at 95.0 %\nCLT method: 19.73 - 21.17 (-3.5%, +3.6%), length = 1.441\n============================================================================\nMedian = 20.32 microns\nConfidence interval at 95.0 %\nrobust method: 19.33 - 21.42 (-4.9%, +5.4%), length = 2.096\n============================================================================\nMode (KDE-based) = 17.66 microns\nMaximum precision set to 0.1\nKDE bandwidth = 2.78 (silverman rule)\n \n============================================================================\nDISTRIBUTION FEATURES\n============================================================================\nSample size (n) = 500\nStandard deviation = 9.07 (1-sigma)\nInterquartile range (IQR) = 11.44\nLognormal shape (Multiplicative Standard Deviation) = 1.49\n============================================================================\nShapiro-Wilk test warnings:\nData is not normally distributed!\nNormality test: 0.88, 0.00 (test statistic, p-value)\n============================================================================\n" ] } ], @@ -295,43 +136,10 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ - " \n", - "============================================================================\n", - "CENTRAL TENDENCY ESTIMATORS\n", - "============================================================================\n", - "Arithmetic mean = 34.79 microns\n", - "Confidence intervals at 95.0 %\n", - "CLT (ASTM) method: 34.09 - 35.48, (±2.0%), length = 1.393\n", - "============================================================================\n", - "Geometric mean = 30.10 microns\n", - "Confidence interval at 95.0 %\n", - "CLT method: 29.47 - 30.75 (-2.1%, +2.2%), length = 1.283\n", - "============================================================================\n", - "Median = 31.53 microns\n", - "Confidence interval at 95.0 %\n", - "robust method: 30.84 - 32.81 (-2.2%, +4.1%), length = 1.970\n", - "============================================================================\n", - "Mode (KDE-based) = 24.31 microns\n", - "Maximum precision set to 0.1\n", - "KDE bandwidth = 4.01 (silverman rule)\n", - " \n", - "============================================================================\n", - "DISTRIBUTION FEATURES\n", - "============================================================================\n", - "Sample size (n) = 2661\n", - "Standard deviation = 18.32 (1-sigma)\n", - "Interquartile range (IQR) = 23.98\n", - "Lognormal shape (Multiplicative Standard Deviation) = 1.75\n", - "============================================================================\n", - "Shapiro-Wilk test warnings:\n", - "Data is not normally distributed!\n", - "Normality test: 0.94, 0.00 (test statistic, p-value)\n", - "Data is not lognormally distributed!\n", - "Lognormality test: 0.99, 0.03 (test statistic, p-value)\n", - "============================================================================\n" + " \n============================================================================\nCENTRAL TENDENCY ESTIMATORS\n============================================================================\nArithmetic mean = 34.79 microns\nConfidence intervals at 95.0 %\nCLT (ASTM) method: 34.09 - 35.48, (±2.0%), length = 1.393\n============================================================================\nGeometric mean = 30.10 microns\nConfidence interval at 95.0 %\nCLT method: 29.47 - 30.75 (-2.1%, +2.2%), length = 1.283\n============================================================================\nMedian = 31.53 microns\nConfidence interval at 95.0 %\nrobust method: 30.84 - 32.81 (-2.2%, +4.1%), length = 1.970\n============================================================================\nMode (KDE-based) = 24.31 microns\nMaximum precision set to 0.1\nKDE bandwidth = 4.01 (silverman rule)\n \n============================================================================\nDISTRIBUTION FEATURES\n============================================================================\nSample size (n) = 2661\nStandard deviation = 18.32 (1-sigma)\nInterquartile range (IQR) = 23.98\nLognormal shape (Multiplicative Standard Deviation) = 1.75\n============================================================================\nShapiro-Wilk test warnings:\nData is not normally distributed!\nNormality test: 0.94, 0.00 (test statistic, p-value)\nData is not lognormally distributed!\nLognormality test: 0.99, 0.03 (test statistic, p-value)\n============================================================================\n" ] } ], @@ -368,66 +176,64 @@ "metadata": {}, "outputs": [ { - "data": { - "text/plain": [ - "\u001b[1;31mSignature:\u001b[0m\n", - "\u001b[0msummarize\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m\n", - "\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", - "\u001b[0m \u001b[0mavg\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'amean'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'gmean'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'median'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'mode'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", - "\u001b[0m \u001b[0mci_level\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0.95\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", - "\u001b[0m \u001b[0mbandwidth\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'silverman'\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", - "\u001b[0m \u001b[0mprecision\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0.1\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", - "\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;31mDocstring:\u001b[0m\n", - "Estimate different grain size statistics. This includes different means,\n", - "the median, the frequency peak grain size via KDE, the confidence intervals\n", - "using different methods, and the distribution features.\n", - "\n", - "Parameters\n", - "----------\n", - "data : array_like\n", - " the size of the grains\n", - "\n", - "avg : string, tuple or list; optional\n", - " the averages to be estimated\n", - "\n", - " | Types:\n", - " | 'amean' - arithmetic mean\n", - " | 'gmean' - geometric mean\n", - " | 'median' - median\n", - " | 'mode' - the kernel-based frequency peak of the distribution\n", - "\n", - "ci_level : scalar between 0 and 1; optional\n", - " the certainty of the confidence interval (default = 0.95)\n", - "\n", - "bandwidth : string {'silverman' or 'scott'} or positive scalar; optional\n", - " the method to estimate the bandwidth or a scalar directly defining the\n", - " bandwidth. It uses the Silverman plug-in method by default.\n", - "\n", - "precision : positive scalar or None; optional\n", - " the maximum precision expected for the \"peak\" kde-based estimator.\n", - " Default is 0.1. Note that this has nothing to do with the\n", - " confidence intervals\n", - "\n", - "Call functions\n", - "--------------\n", - "- amean, gmean, median, and freq_peak (from averages)\n", - "\n", - "Examples\n", - "--------\n", - ">>> summarize(dataset['diameters'])\n", - ">>> summarize(dataset['diameters'], ci_level=0.99)\n", - ">>> summarize(np.log(dataset['diameters']), avg=('amean', 'median', 'mode'))\n", - "\n", - "Returns\n", - "-------\n", - "None\n", - "\u001b[1;31mFile:\u001b[0m c:\\users\\marco\\documents\\github\\grainsizetools\\grain_size_tools\\grainsizetools_script.py\n", - "\u001b[1;31mType:\u001b[0m function\n" - ] - }, - "metadata": {}, - "output_type": "display_data" + "output_type": "stream", + "text": [ + "\u001b[1;31mSignature:\u001b[0m\n", + "\u001b[0msummarize\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m\n", + "\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", + "\u001b[0m \u001b[0mavg\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'amean'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'gmean'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'median'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'mode'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", + "\u001b[0m \u001b[0mci_level\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0.95\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", + "\u001b[0m \u001b[0mbandwidth\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'silverman'\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", + "\u001b[0m \u001b[0mprecision\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0.1\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", + "\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;31mDocstring:\u001b[0m\n", + "Estimate different grain size statistics. This includes different means,\n", + "the median, the frequency peak grain size via KDE, the confidence intervals\n", + "using different methods, and the distribution features.\n", + "\n", + "Parameters\n", + "----------\n", + "data : array_like\n", + " the size of the grains\n", + "\n", + "avg : string, tuple or list; optional\n", + " the averages to be estimated\n", + "\n", + " | Types:\n", + " | 'amean' - arithmetic mean\n", + " | 'gmean' - geometric mean\n", + " | 'median' - median\n", + " | 'mode' - the kernel-based frequency peak of the distribution\n", + "\n", + "ci_level : scalar between 0 and 1; optional\n", + " the certainty of the confidence interval (default = 0.95)\n", + "\n", + "bandwidth : string {'silverman' or 'scott'} or positive scalar; optional\n", + " the method to estimate the bandwidth or a scalar directly defining the\n", + " bandwidth. It uses the Silverman plug-in method by default.\n", + "\n", + "precision : positive scalar or None; optional\n", + " the maximum precision expected for the \"peak\" kde-based estimator.\n", + " Default is 0.1. Note that this is not related with the confidence\n", + " intervals\n", + "\n", + "Call functions\n", + "--------------\n", + "- amean, gmean, median, and freq_peak (from averages)\n", + "\n", + "Examples\n", + "--------\n", + ">>> summarize(dataset['diameters'])\n", + ">>> summarize(dataset['diameters'], ci_level=0.99)\n", + ">>> summarize(np.log(dataset['diameters']), avg=('amean', 'median', 'mode'))\n", + "\n", + "Returns\n", + "-------\n", + "None\n", + "\u001b[1;31mFile:\u001b[0m c:\\users\\marco\\documents\\github\\grainsizetools\\grain_size_tools\\grainsizetools_script.py\n", + "\u001b[1;31mType:\u001b[0m function\n" + ], + "name": "stdout" } ], "source": [ @@ -460,9 +266,9 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.7" + "version": "3.7.9-final" } }, "nbformat": 4, "nbformat_minor": 4 -} +} \ No newline at end of file diff --git a/grain_size_tools/example_notebooks/paleopiezometry_examples.ipynb b/grain_size_tools/example_notebooks/paleopiezometry_examples.ipynb index 9f1ed7e..01848d8 100644 --- a/grain_size_tools/example_notebooks/paleopiezometry_examples.ipynb +++ b/grain_size_tools/example_notebooks/paleopiezometry_examples.ipynb @@ -13,26 +13,10 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ - "module plot imported\n", - "module averages imported\n", - "module stereology imported\n", - "module piezometers imported\n", - "module template imported\n", - "\n", - "======================================================================================\n", - "Welcome to GrainSizeTools script\n", - "======================================================================================\n", - "A free open-source cross-platform script to visualize and characterize grain size\n", - "population and estimate differential stress via paleopizometers.\n", - "\n", - "Version: v3.0RC0 (2020-04-23)\n", - "Documentation: https://marcoalopez.github.io/GrainSizeTools/\n", - "\n", - "Type get.functions_list() to get a list of the main methods\n", - "\n" + "module plot imported\nmodule averages imported\nmodule stereology imported\nmodule piezometers imported\nmodule template imported\n\n======================================================================================\nWelcome to GrainSizeTools script\n======================================================================================\nA free open-source cross-platform script to visualize and characterize grain size\npopulation and estimate differential stress via paleopizometers.\n\nVersion: v3.0.2 (2020-12-30)\nDocumentation: https://marcoalopez.github.io/GrainSizeTools/\n\nType get.functions_list() to get a list of the main methods\n\n" ] } ], @@ -89,18 +73,10 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ - "Available piezometers:\n", - "'Cross'\n", - "'Cross_hr'\n", - "'Holyoke'\n", - "'Holyoke_BLG'\n", - "'Shimizu'\n", - "'Stipp_Tullis'\n", - "'Stipp_Tullis_BLG'\n", - "'Twiss'\n" + "Available piezometers:\n'Cross'\n'Cross_hr'\n'Holyoke'\n'Holyoke_BLG'\n'Shimizu'\n'Stipp_Tullis'\n'Stipp_Tullis_BLG'\n'Twiss'\n" ] } ], @@ -121,6 +97,7 @@ "metadata": {}, "outputs": [ { + "output_type": "execute_result", "data": { "text/plain": [ "(550,\n", @@ -130,9 +107,8 @@ " 1.5)" ] }, - "execution_count": 4, "metadata": {}, - "output_type": "execute_result" + "execution_count": 4 } ], "source": [ @@ -161,71 +137,69 @@ "metadata": {}, "outputs": [ { - "data": { - "text/plain": [ - "\u001b[1;31mSignature:\u001b[0m \u001b[0mcalc_diffstress\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mgrain_size\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mphase\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mpiezometer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcorrection\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;31mDocstring:\u001b[0m\n", - "Apply different piezometric relations to estimate the differential\n", - "stress from average apparent grain sizes. The piezometric relation has\n", - "the following general form:\n", - "\n", - "df = B * grain_size**-m\n", - "\n", - "where df is the differential stress in [MPa], B is an experimentally\n", - "derived parameter in [MPa micron**m], grain_size is the aparent grain\n", - "size in [microns], and m is an experimentally derived exponent.\n", - "\n", - "Parameters\n", - "----------\n", - "grain_size : positive scalar or array-like\n", - " the apparent grain size in microns\n", - "\n", - "phase : string {'quartz', 'olivine', 'calcite', or 'feldspar'}\n", - " the mineral phase\n", - "\n", - "piezometer : string\n", - " the piezometric relation\n", - "\n", - "correction : bool, default False\n", - " correct the stress values for plane stress (Paterson and Olgaard, 2000)\n", - "\n", - " References\n", - "-----------\n", - "Paterson and Olgaard (2000) https://doi.org/10.1016/S0191-8141(00)00042-0\n", - "de Hoff and Rhines (1968) Quantitative Microscopy. Mcgraw-Hill. New York.\n", - "\n", - "Call functions\n", - "--------------\n", - "piezometers.quartz\n", - "piezometers.olivine\n", - "piezometers.calcite\n", - "piezometers.albite\n", - "\n", - "Assumptions\n", - "-----------\n", - "- Independence of temperature (excepting Shimizu piezometer), total strain,\n", - "flow stress, and water content.\n", - "- Recrystallized grains are equidimensional or close to equidimensional when\n", - "using a single section.\n", - "- The piezometer relations requires entering the grain size as \"average\"\n", - "apparent grain size values calculated using equivalent circular diameters\n", - "(ECD) with no stereological correction. See documentation for more details.\n", - "- When required, the grain size value will be converted from ECD to linear\n", - "intercept (LI) using a correction factor based on de Hoff and Rhines (1968):\n", - "LI = (correction factor / sqrt(4/pi)) * ECD\n", - "- Stress estimates can be corrected from uniaxial compression (experiments)\n", - "to plane strain (nature) multiplying the paleopiezometer by 2/sqrt(3)\n", - "(Paterson and Olgaard, 2000)\n", - "\n", - "Returns\n", - "-------\n", - "The differential stress in MPa (a float)\n", - "\u001b[1;31mFile:\u001b[0m c:\\users\\marco\\documents\\github\\grainsizetools\\grain_size_tools\\grainsizetools_script.py\n", - "\u001b[1;31mType:\u001b[0m function\n" - ] - }, - "metadata": {}, - "output_type": "display_data" + "output_type": "stream", + "text": [ + "\u001b[1;31mSignature:\u001b[0m \u001b[0mcalc_diffstress\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mgrain_size\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mphase\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mpiezometer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcorrection\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;31mDocstring:\u001b[0m\n", + "Apply different piezometric relations to estimate the differential\n", + "stress from average apparent grain sizes. The piezometric relation has\n", + "the following general form:\n", + "\n", + "df = B * grain_size**-m\n", + "\n", + "where df is the differential stress in [MPa], B is an experimentally\n", + "derived parameter in [MPa micron**m], grain_size is the aparent grain\n", + "size in [microns], and m is an experimentally derived exponent.\n", + "\n", + "Parameters\n", + "----------\n", + "grain_size : positive scalar or array-like\n", + " the apparent grain size in microns\n", + "\n", + "phase : string {'quartz', 'olivine', 'calcite', or 'feldspar'}\n", + " the mineral phase\n", + "\n", + "piezometer : string\n", + " the piezometric relation\n", + "\n", + "correction : bool, default False\n", + " correct the stress values for plane stress (Paterson and Olgaard, 2000)\n", + "\n", + " References\n", + "-----------\n", + "Paterson and Olgaard (2000) https://doi.org/10.1016/S0191-8141(00)00042-0\n", + "de Hoff and Rhines (1968) Quantitative Microscopy. Mcgraw-Hill. New York.\n", + "\n", + "Call functions\n", + "--------------\n", + "piezometers.quartz\n", + "piezometers.olivine\n", + "piezometers.calcite\n", + "piezometers.albite\n", + "\n", + "Assumptions\n", + "-----------\n", + "- Independence of temperature (excepting Shimizu piezometer), total strain,\n", + "flow stress, and water content.\n", + "- Recrystallized grains are equidimensional or close to equidimensional when\n", + "using a single section.\n", + "- The piezometer relations requires entering the grain size as \"average\"\n", + "apparent grain size values calculated using equivalent circular diameters\n", + "(ECD) with no stereological correction. See documentation for more details.\n", + "- When required, the grain size value will be converted from ECD to linear\n", + "intercept (LI) using a correction factor based on de Hoff and Rhines (1968):\n", + "LI = (correction factor / sqrt(4/pi)) * ECD\n", + "- Stress estimates can be corrected from uniaxial compression (experiments)\n", + "to plane strain (nature) multiplying the paleopiezometer by 2/sqrt(3)\n", + "(Paterson and Olgaard, 2000)\n", + "\n", + "Returns\n", + "-------\n", + "The differential stress in MPa (a float)\n", + "\u001b[1;31mFile:\u001b[0m c:\\users\\marco\\documents\\github\\grainsizetools\\grain_size_tools\\grainsizetools_script.py\n", + "\u001b[1;31mType:\u001b[0m function\n" + ], + "name": "stdout" } ], "source": [ @@ -245,16 +219,10 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ - "============================================================================\n", - "differential stress = 83.65 MPa\n", - "\n", - "INFO:\n", - "Ensure that you entered the apparent grain size as the arithmetic mean grain size\n", - "ECD was converted to linear intercepts using de Hoff and Rhines (1968) correction\n", - "============================================================================\n" + "============================================================================\ndifferential stress = 83.65 MPa\n\nINFO:\nEnsure that you entered the apparent grain size as the arithmetic mean grain size\nECD was converted to linear intercepts using de Hoff and Rhines (1968) correction\n============================================================================\n" ] } ], @@ -275,8 +243,8 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ "============================================================================\n", "differential stress = 96.59 MPa\n", @@ -305,6 +273,7 @@ "metadata": {}, "outputs": [ { + "output_type": "execute_result", "data": { "text/plain": [ "(669.0,\n", @@ -314,9 +283,8 @@ " False)" ] }, - "execution_count": 8, "metadata": {}, - "output_type": "execute_result" + "execution_count": 8 } ], "source": [ @@ -337,15 +305,10 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ - "============================================================================\n", - "differential stress = 36.79 MPa\n", - "\n", - "INFO:\n", - "Ensure that you entered the apparent grain size as the root mean square (RMS)\n", - "============================================================================\n" + "============================================================================\ndifferential stress = 36.79 MPa\n\nINFO:\nEnsure that you entered the apparent grain size as the root mean square (RMS)\n============================================================================\n" ] } ], @@ -376,25 +339,21 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ - "============================================================================\n", - "INFO:\n", - "Ensure that you entered the apparent grain size as the arithmetic mean in linear scale\n", - "ECD was converted to linear intercepts using de Hoff and Rhines (1968) correction\n", - "Differential stresses in MPa\n" + "============================================================================\nINFO:\nEnsure that you entered the apparent grain size as the arithmetic mean in linear scale\nECD was converted to linear intercepts using de Hoff and Rhines (1968) correction\nDifferential stresses in MPa\n" ] }, { + "output_type": "execute_result", "data": { "text/plain": [ "array([167.41, 153.66, 162.16, 172.73, 162.83, 185.45])" ] }, - "execution_count": 10, "metadata": {}, - "output_type": "execute_result" + "execution_count": 10 } ], "source": [ @@ -416,41 +375,39 @@ "metadata": {}, "outputs": [ { - "data": { - "text/plain": [ - "\u001b[1;31mSignature:\u001b[0m \u001b[0mconf_interval\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mconfidence\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0.95\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;31mDocstring:\u001b[0m\n", - "Estimate the confidence interval using the t-distribution with n-1\n", - "degrees of freedom t(n-1). This is the way to go when sample size is\n", - "small (n < 30) and the standard deviation cannot be estimated accurately.\n", - "For large datasets, the t-distribution approaches the normal distribution.\n", - "\n", - "Parameters\n", - "----------\n", - "data : array-like\n", - " the dataset\n", - "\n", - "confidence : float between 0 and 1, optional\n", - " the confidence interval, default = 0.95\n", - "\n", - "Assumptions\n", - "-----------\n", - "the data follows a normal or symmetric distrubution (when sample size\n", - "is large)\n", - "\n", - "call_function(s)\n", - "----------------\n", - "Scipy's t.interval\n", - "\n", - "Returns\n", - "-------\n", - "the arithmetic mean, the error, and the limits of the confidence interval\n", - "\u001b[1;31mFile:\u001b[0m c:\\users\\marco\\documents\\github\\grainsizetools\\grain_size_tools\\grainsizetools_script.py\n", - "\u001b[1;31mType:\u001b[0m function\n" - ] - }, - "metadata": {}, - "output_type": "display_data" + "output_type": "stream", + "text": [ + "\u001b[1;31mSignature:\u001b[0m \u001b[0mconf_interval\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mconfidence\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0.95\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;31mDocstring:\u001b[0m\n", + "Estimate the confidence interval using the t-distribution with n-1\n", + "degrees of freedom t(n-1). This is the way to go when sample size is\n", + "small (n < 30) and the standard deviation cannot be estimated accurately.\n", + "For large datasets, the t-distribution approaches the normal distribution.\n", + "\n", + "Parameters\n", + "----------\n", + "data : array-like\n", + " the dataset\n", + "\n", + "confidence : float between 0 and 1, optional\n", + " the confidence interval, default = 0.95\n", + "\n", + "Assumptions\n", + "-----------\n", + "the data follows a normal or symmetric distrubution (when sample size\n", + "is large)\n", + "\n", + "call_function(s)\n", + "----------------\n", + "Scipy's t.interval\n", + "\n", + "Returns\n", + "-------\n", + "the arithmetic mean, the error, and the limits of the confidence interval\n", + "\u001b[1;31mFile:\u001b[0m c:\\users\\marco\\documents\\github\\grainsizetools\\grain_size_tools\\grainsizetools_script.py\n", + "\u001b[1;31mType:\u001b[0m function\n" + ], + "name": "stdout" } ], "source": [ @@ -463,8 +420,8 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ " \n", "Mean = 167.37 ± 11.41\n", @@ -474,14 +431,14 @@ ] }, { + "output_type": "execute_result", "data": { "text/plain": [ "(167.37333333333333, 11.412701448126, (155.96063188520733, 178.78603478145934))" ] }, - "execution_count": 12, "metadata": {}, - "output_type": "execute_result" + "execution_count": 12 } ], "source": [ @@ -505,9 +462,9 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.7" + "version": "3.7.9-final" } }, "nbformat": 4, "nbformat_minor": 4 -} +} \ No newline at end of file diff --git a/grain_size_tools/example_notebooks/plot_module_examples.ipynb b/grain_size_tools/example_notebooks/plot_module_examples.ipynb index 279dbdb..2f28b08 100644 --- a/grain_size_tools/example_notebooks/plot_module_examples.ipynb +++ b/grain_size_tools/example_notebooks/plot_module_examples.ipynb @@ -15,26 +15,10 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ - "module plot imported\n", - "module averages imported\n", - "module stereology imported\n", - "module piezometers imported\n", - "module template imported\n", - "\n", - "======================================================================================\n", - "Welcome to GrainSizeTools script\n", - "======================================================================================\n", - "A free open-source cross-platform script to visualize and characterize grain size\n", - "population and estimate differential stress via paleopizometers.\n", - "\n", - "Version: v3.0RC0 (2020-04-23)\n", - "Documentation: https://marcoalopez.github.io/GrainSizeTools/\n", - "\n", - "Type get.functions_list() to get a list of the main methods\n", - "\n" + "module plot imported\nmodule averages imported\nmodule stereology imported\nmodule piezometers imported\nmodule template imported\n\n======================================================================================\nWelcome to GrainSizeTools script\n======================================================================================\nA free open-source cross-platform script to visualize and characterize grain size\npopulation and estimate differential stress via paleopizometers.\n\nVersion: v3.0.2 (2020-12-30)\nDocumentation: https://marcoalopez.github.io/GrainSizeTools/\n\nType get.functions_list() to get a list of the main methods\n\n" ] } ], @@ -49,211 +33,8 @@ "metadata": {}, "outputs": [ { + "output_type": "execute_result", "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
AreaCirc.FeretFeretXFeretYFeretAngleMinFeretARRoundSoliditydiameters
01157.250.68018.0621535.00.5131.63413.5001.1010.9080.93714.149803
122059.750.77162.097753.516.5165.06946.6971.3140.7610.97251.210889
231961.500.84257.871727.065.071.87846.9231.1390.8780.97249.974587
345428.500.709114.6571494.583.519.62063.4491.8960.5280.94783.137121
45374.000.69929.2622328.034.033.14716.0001.5150.6600.97021.821815
.......................................
26562657452.500.78928.5041368.01565.5127.87522.5001.2350.8100.96024.002935
265726581081.250.75647.9091349.51569.5108.24631.3631.4460.6920.96037.103777
26582659513.500.72032.9621373.01586.0112.28620.4961.4930.6700.95325.569679
26592660277.750.62729.4361316.01601.5159.10217.0021.7270.5790.92018.805379
26602661725.000.74839.4371335.51615.5129.34128.0251.3510.7400.96030.382539
\n", - "

2661 rows × 12 columns

\n", - "
" - ], "text/plain": [ " Area Circ. Feret FeretX FeretY FeretAngle MinFeret \\\n", "0 1 157.25 0.680 18.062 1535.0 0.5 131.634 13.500 \n", @@ -282,11 +63,11 @@ "2660 1.351 0.740 0.960 30.382539 \n", "\n", "[2661 rows x 12 columns]" - ] + ], + "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
AreaCirc.FeretFeretXFeretYFeretAngleMinFeretARRoundSoliditydiameters
01157.250.68018.0621535.00.5131.63413.5001.1010.9080.93714.149803
122059.750.77162.097753.516.5165.06946.6971.3140.7610.97251.210889
231961.500.84257.871727.065.071.87846.9231.1390.8780.97249.974587
345428.500.709114.6571494.583.519.62063.4491.8960.5280.94783.137121
45374.000.69929.2622328.034.033.14716.0001.5150.6600.97021.821815
.......................................
26562657452.500.78928.5041368.01565.5127.87522.5001.2350.8100.96024.002935
265726581081.250.75647.9091349.51569.5108.24631.3631.4460.6920.96037.103777
26582659513.500.72032.9621373.01586.0112.28620.4961.4930.6700.95325.569679
26592660277.750.62729.4361316.01601.5159.10217.0021.7270.5790.92018.805379
26602661725.000.74839.4371335.51615.5129.34128.0251.3510.7400.96030.382539
\n

2661 rows × 12 columns

\n
" }, - "execution_count": 2, "metadata": {}, - "output_type": "execute_result" + "execution_count": 2 } ], "source": [ @@ -314,27 +95,20 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ - "=======================================\n", - "Number of classes = 45\n", - "binsize = 3.41\n", - "=======================================\n", - "=======================================\n", - "KDE bandwidth = 4.01\n", - "=======================================\n" + "=======================================\nNumber of classes = 45\nbinsize = 3.41\n=======================================\n=======================================\nKDE bandwidth = 4.01\n=======================================\n" ] }, { + "output_type": "display_data", "data": { - "image/png": "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\n", - "text/plain": [ - "
" - ] + "text/plain": "
", + "image/svg+xml": "\r\n\r\n\r\n\r\n \r\n \r\n \r\n \r\n 2020-12-31T14:06:32.599001\r\n image/svg+xml\r\n \r\n \r\n Matplotlib v3.3.2, https://matplotlib.org/\r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n\r\n", + "image/png": "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\n" }, - "metadata": {}, - "output_type": "display_data" + "metadata": {} } ], "source": [ @@ -384,77 +158,75 @@ "metadata": {}, "outputs": [ { - "data": { - "text/plain": [ - "\u001b[1;31mSignature:\u001b[0m\n", - "\u001b[0mplot\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdistribution\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m\n", - "\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", - "\u001b[0m \u001b[0mplot\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'hist'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'kde'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", - "\u001b[0m \u001b[0mavg\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'amean'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'gmean'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'median'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'mode'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", - "\u001b[0m \u001b[0mbinsize\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'auto'\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", - "\u001b[0m \u001b[0mbandwidth\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'silverman'\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", - "\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mfig_kw\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", - "\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;31mDocstring:\u001b[0m\n", - "Return a plot with the ditribution of (apparent or actual) grain sizes\n", - "in a dataset.\n", - "\n", - "Parameters\n", - "----------\n", - "data : array_like\n", - " the size of the grains\n", - "\n", - "plot : string, tuple or list; optional\n", - " the type of plot, either histogram ('hist'), kernel density estimate\n", - " ('kde') or both ('hist', 'kde'). Default is both.\n", - "\n", - "avg : string, tuple or list; optional\n", - " the central tendency measures o show, either the arithmetic ('amean')\n", - " or geometric ('gmean') means, the median ('median'), and/or the\n", - " KDE-based mode ('mode'). Default all averages.\n", - "\n", - "binsize : string or positive scalar; optional\n", - " If 'auto', it defines the plug-in method to calculate the bin size.\n", - " When integer or float, it directly specifies the bin size.\n", - " Default: the 'auto' method.\n", - "\n", - " | Available plug-in methods:\n", - " | 'auto' (fd if sample_size > 1000 or Sturges otherwise)\n", - " | 'doane' (Doane's rule)\n", - " | 'fd' (Freedman-Diaconis rule)\n", - " | 'rice' (Rice's rule)\n", - " | 'scott' (Scott rule)\n", - " | 'sqrt' (square-root rule)\n", - " | 'sturges' (Sturge's rule)\n", - "\n", - "bandwidth : string {'silverman' or 'scott'} or positive scalar; optional\n", - " the method to estimate the bandwidth or a scalar directly defining the\n", - " bandwidth. It uses the Silverman plug-in method by default.\n", - "\n", - "**fig_kw :\n", - " additional keyword arguments to control the size (figsize) and\n", - " resolution (dpi) of the plot. Default figsize is (6.4, 4.8).\n", - " Default resolution is 100 dpi.\n", - "\n", - "Call functions\n", - "--------------\n", - "- gaussian_kde (from Scipy stats)\n", - "\n", - "Examples\n", - "--------\n", - ">>> distribution(data['diameters'])\n", - ">>> distribution(data['diameters'], figsize=(6.4, 4.8))\n", - "\n", - "Returns\n", - "-------\n", - "A plot showing the distribution of (apparent) grain sizes and\n", - "the location of the averages defined.\n", - "\u001b[1;31mFile:\u001b[0m c:\\users\\marco\\documents\\github\\grainsizetools\\grain_size_tools\\plot.py\n", - "\u001b[1;31mType:\u001b[0m function\n" - ] - }, - "metadata": {}, - "output_type": "display_data" + "output_type": "stream", + "text": [ + "\u001b[1;31mSignature:\u001b[0m\n", + "\u001b[0mplot\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdistribution\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m\n", + "\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", + "\u001b[0m \u001b[0mplot\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'hist'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'kde'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", + "\u001b[0m \u001b[0mavg\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'amean'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'gmean'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'median'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'mode'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", + "\u001b[0m \u001b[0mbinsize\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'auto'\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", + "\u001b[0m \u001b[0mbandwidth\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'silverman'\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", + "\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mfig_kw\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", + "\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;31mDocstring:\u001b[0m\n", + "Return a plot with the ditribution of (apparent or actual) grain sizes\n", + "in a dataset.\n", + "\n", + "Parameters\n", + "----------\n", + "data : array_like\n", + " the size of the grains\n", + "\n", + "plot : string, tuple or list; optional\n", + " the type of plot, either histogram ('hist'), kernel density estimate\n", + " ('kde') or both ('hist', 'kde'). Default is both.\n", + "\n", + "avg : string, tuple or list; optional\n", + " the central tendency measures o show, either the arithmetic ('amean')\n", + " or geometric ('gmean') means, the median ('median'), and/or the\n", + " KDE-based mode ('mode'). Default all averages.\n", + "\n", + "binsize : string or positive scalar; optional\n", + " If 'auto', it defines the plug-in method to calculate the bin size.\n", + " When integer or float, it directly specifies the bin size.\n", + " Default: the 'auto' method.\n", + "\n", + " | Available plug-in methods:\n", + " | 'auto' (fd if sample_size > 1000 or Sturges otherwise)\n", + " | 'doane' (Doane's rule)\n", + " | 'fd' (Freedman-Diaconis rule)\n", + " | 'rice' (Rice's rule)\n", + " | 'scott' (Scott rule)\n", + " | 'sqrt' (square-root rule)\n", + " | 'sturges' (Sturge's rule)\n", + "\n", + "bandwidth : string {'silverman' or 'scott'} or positive scalar; optional\n", + " the method to estimate the bandwidth or a scalar directly defining the\n", + " bandwidth. It uses the Silverman plug-in method by default.\n", + "\n", + "**fig_kw :\n", + " additional keyword arguments to control the size (figsize) and\n", + " resolution (dpi) of the plot. Default figsize is (6.4, 4.8).\n", + " Default resolution is 100 dpi.\n", + "\n", + "Call functions\n", + "--------------\n", + "- gaussian_kde (from Scipy stats)\n", + "\n", + "Examples\n", + "--------\n", + ">>> distribution(data['diameters'])\n", + ">>> distribution(data['diameters'], figsize=(6.4, 4.8))\n", + "\n", + "Returns\n", + "-------\n", + "A plot showing the distribution of (apparent) grain sizes and\n", + "the location of the averages defined.\n", + "\u001b[1;31mFile:\u001b[0m c:\\users\\marco\\documents\\github\\grainsizetools\\grain_size_tools\\plot.py\n", + "\u001b[1;31mType:\u001b[0m function\n" + ], + "name": "stdout" } ], "source": [ @@ -486,26 +258,20 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ - "=======================================\n", - "Shapiro-Wilk test (lognormal):\n", - "0.98, 0.00 (test statistic, p-value)\n", - "It doesnt look like a lognormal distribution (p-value < 0.05)\n", - "(╯°□°）╯︵ ┻━┻\n", - "=======================================\n" + "=======================================\nShapiro-Wilk test (lognormal):\n0.98, 0.01 (test statistic, p-value)\nIt doesnt look like a lognormal distribution (p-value < 0.05)\n(╯°□°）╯︵ ┻━┻\n=======================================\n" ] }, { + "output_type": "display_data", "data": { - "image/png": "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\n", - "text/plain": [ - "
" - ] + "text/plain": "
", + "image/svg+xml": "\r\n\r\n\r\n\r\n \r\n \r\n \r\n \r\n 2020-12-31T14:06:33.121500\r\n image/svg+xml\r\n \r\n \r\n Matplotlib v3.3.2, https://matplotlib.org/\r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n\r\n", + "image/png": "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\n" }, - "metadata": {}, - "output_type": "display_data" + "metadata": {} } ], "source": [ @@ -542,29 +308,20 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ - "=======================================\n", - "DESCRIPTIVE STATISTICS\n", - "Area-weighted mean grain size = 53.88 microns\n", - "=======================================\n", - "HISTOGRAM FEATURES\n", - "The modal interval is 40.85 - 44.26 microns\n", - "The number of classes are 46\n", - "The bin size is 3.40 according to the auto rule\n", - "=======================================\n" + "=======================================\nDESCRIPTIVE STATISTICS\nArea-weighted mean grain size = 53.88 microns\n=======================================\nHISTOGRAM FEATURES\nThe modal interval is 40.85 - 44.26 microns\nThe number of classes are 46\nThe bin size is 3.40 according to the auto rule\n=======================================\n" ] }, { + "output_type": "display_data", "data": { - "image/png": "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\n", - "text/plain": [ - "
" - ] + "text/plain": "
", + "image/svg+xml": "\r\n\r\n\r\n\r\n \r\n \r\n \r\n \r\n 2020-12-31T14:06:33.512693\r\n image/svg+xml\r\n \r\n \r\n Matplotlib v3.3.2, https://matplotlib.org/\r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n\r\n", + "image/png": "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\n" }, - "metadata": {}, - "output_type": "display_data" + "metadata": {} } ], "source": [ @@ -599,24 +356,20 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ - "=======================================\n", - "Normalized SD = 0.165\n", - "KDE bandwidth = 0.04\n", - "=======================================\n" + "=======================================\nNormalized SD = 0.165\nKDE bandwidth = 0.04\n=======================================\n" ] }, { + "output_type": "display_data", "data": { - "image/png": "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\n", - "text/plain": [ - "
" - ] + "text/plain": "
", + "image/svg+xml": "\r\n\r\n\r\n\r\n \r\n \r\n \r\n \r\n 2020-12-31T14:06:33.952986\r\n image/svg+xml\r\n \r\n \r\n Matplotlib v3.3.2, https://matplotlib.org/\r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n\r\n", + "image/png": "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\n" }, - "metadata": {}, - "output_type": "display_data" + "metadata": {} } ], "source": [ @@ -645,35 +398,31 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ - "=======================================\n", - "Normalized IQR = 0.221\n", - "KDE bandwidth = 0.1\n", - "=======================================\n" + "=======================================\nNormalized IQR = 0.221\nKDE bandwidth = 0.1\n=======================================\n" ] }, { + "output_type": "execute_result", "data": { "text/plain": [ "(
,\n", - " )" + " )" ] }, - "execution_count": 12, "metadata": {}, - "output_type": "execute_result" + "execution_count": 12 }, { + "output_type": "display_data", "data": { - "image/png": "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\n", - "text/plain": [ - "
" - ] + "text/plain": "
", + "image/svg+xml": "\r\n\r\n\r\n\r\n \r\n \r\n \r\n \r\n 2020-12-31T14:06:34.351743\r\n image/svg+xml\r\n \r\n \r\n Matplotlib v3.3.2, https://matplotlib.org/\r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n\r\n", + "image/png": "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\n" }, - "metadata": {}, - "output_type": "display_data" + "metadata": {} } ], "source": [ @@ -711,9 +460,9 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.7" + "version": "3.7.9-final" } }, "nbformat": 4, "nbformat_minor": 4 -} +} \ No newline at end of file diff --git a/grain_size_tools/example_notebooks/stereology_module_examples.ipynb b/grain_size_tools/example_notebooks/stereology_module_examples.ipynb index fa4e03f..d0dd144 100644 --- a/grain_size_tools/example_notebooks/stereology_module_examples.ipynb +++ b/grain_size_tools/example_notebooks/stereology_module_examples.ipynb @@ -17,26 +17,10 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ - "module plot imported\n", - "module averages imported\n", - "module stereology imported\n", - "module piezometers imported\n", - "module template imported\n", - "\n", - "======================================================================================\n", - "Welcome to GrainSizeTools script\n", - "======================================================================================\n", - "A free open-source cross-platform script to visualize and characterize grain size\n", - "population and estimate differential stress via paleopizometers.\n", - "\n", - "Version: v3.0RC0 (2020-04-23)\n", - "Documentation: https://marcoalopez.github.io/GrainSizeTools/\n", - "\n", - "Type get.functions_list() to get a list of the main methods\n", - "\n" + "module plot imported\nmodule averages imported\nmodule stereology imported\nmodule piezometers imported\nmodule template imported\n\n======================================================================================\nWelcome to GrainSizeTools script\n======================================================================================\nA free open-source cross-platform script to visualize and characterize grain size\npopulation and estimate differential stress via paleopizometers.\n\nVersion: v3.0.2 (2020-12-30)\nDocumentation: https://marcoalopez.github.io/GrainSizeTools/\n\nType get.functions_list() to get a list of the main methods\n\n" ] } ], @@ -90,26 +74,20 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ - "=======================================\n", - "volume fraction (up to 50 microns) = 41.65 %\n", - "=======================================\n", - "=======================================\n", - "bin size = 14.24\n", - "=======================================\n" + "=======================================\nvolume fraction (up to 50 microns) = 41.65 %\n=======================================\n=======================================\nbin size = 14.24\n=======================================\n" ] }, { + "output_type": "display_data", "data": { - "image/png": "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\n", - "text/plain": [ - "
" - ] + "text/plain": "
", + "image/svg+xml": "\r\n\r\n\r\n\r\n \r\n \r\n \r\n \r\n 2020-12-31T14:09:14.386754\r\n image/svg+xml\r\n \r\n \r\n Matplotlib v3.3.2, https://matplotlib.org/\r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n\r\n", + "image/png": "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\n" }, - "metadata": {}, - "output_type": "display_data" + "metadata": {} } ], "source": [ @@ -138,76 +116,74 @@ "metadata": {}, "outputs": [ { - "data": { - "text/plain": [ - "\u001b[1;31mSignature:\u001b[0m\n", - "\u001b[0mstereology\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mSaltykov\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m\n", - "\u001b[0m \u001b[0mdiameters\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", - "\u001b[0m \u001b[0mnumbins\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m10\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", - "\u001b[0m \u001b[0mcalc_vol\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", - "\u001b[0m \u001b[0mtext_file\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", - "\u001b[0m \u001b[0mreturn_data\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", - "\u001b[0m \u001b[0mleft_edge\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", - "\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;31mDocstring:\u001b[0m\n", - "Estimate the actual (3D) distribution of grain size from the population\n", - "of apparent diameters measured in a thin section using a Saltykov-type\n", - "algorithm (Saltykov 1967; Sahagian and Proussevitch 1998).\n", - "\n", - "The Saltykov method is optimal to estimate the volume of a particular grain\n", - "size fraction as well as to obtain a qualitative view of the appearance of\n", - "the actual 3D grain size population, either in uni- or multimodal populations.\n", - "\n", - "Parameters\n", - "----------\n", - "diameters : array_like\n", - " the apparent diameters of the grains.\n", - "\n", - "numbins : positive integer, optional\n", - " the number of bins/classes of the histogram. If not declared,\n", - " is set to 10 by default.\n", - "\n", - "calc_vol : positive scalar or None, optional\n", - " if the user specifies a diameter, the function will return the volume\n", - " occupied by the grain fraction up to that diameter.\n", - "\n", - "text_file : string or None, optional\n", - " if the user specifies a name, the function will store a csv file\n", - " with that name containing the Saltykov output.\n", - "\n", - "return_data : bool, optional\n", - " if True the function will return the position of the midpoints and\n", - " the frequencies.\n", - "\n", - "left_edge : positive scalar or 'min', optional\n", - " set the left edge of the histogram. Default is zero.\n", - "\n", - "Call functions\n", - "--------------\n", - "- unfold_population\n", - "- Saltykov_plot\n", - "\n", - "Examples\n", - "--------\n", - ">>> Saltykov(diameters)\n", - ">>> Saltykov(diameters, numbins=16, calc_vol=40)\n", - ">>> Saltykov(diameters, text_file='foo.csv')\n", - ">>> mid_points, frequencies = Saltykov(diameters, return_data=True)\n", - "\n", - "References\n", - "----------\n", - "Saltykov SA (1967) http://doi.org/10.1007/978-3-642-88260-9_31\n", - "Sahagian and Proussevitch (1998) https://doi.org/10.1016/S0377-0273(98)00043-2\n", - "\n", - "Return\n", - "------\n", - "Statistical descriptors, a plot, and/or a file with the data (optional)\n", - "\u001b[1;31mFile:\u001b[0m c:\\users\\marco\\documents\\github\\grainsizetools\\grain_size_tools\\stereology.py\n", - "\u001b[1;31mType:\u001b[0m function\n" - ] - }, - "metadata": {}, - "output_type": "display_data" + "output_type": "stream", + "text": [ + "\u001b[1;31mSignature:\u001b[0m\n", + "\u001b[0mstereology\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mSaltykov\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m\n", + "\u001b[0m \u001b[0mdiameters\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", + "\u001b[0m \u001b[0mnumbins\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m10\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", + "\u001b[0m \u001b[0mcalc_vol\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", + "\u001b[0m \u001b[0mtext_file\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", + "\u001b[0m \u001b[0mreturn_data\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", + "\u001b[0m \u001b[0mleft_edge\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\n", + "\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;31mDocstring:\u001b[0m\n", + "Estimate the actual (3D) distribution of grain size from the population\n", + "of apparent diameters measured in a thin section using a Saltykov-type\n", + "algorithm (Saltykov 1967; Sahagian and Proussevitch 1998).\n", + "\n", + "The Saltykov method is optimal to estimate the volume of a particular grain\n", + "size fraction as well as to obtain a qualitative view of the appearance of\n", + "the actual 3D grain size population, either in uni- or multimodal populations.\n", + "\n", + "Parameters\n", + "----------\n", + "diameters : array_like\n", + " the apparent diameters of the grains.\n", + "\n", + "numbins : positive integer, optional\n", + " the number of bins/classes of the histogram. If not declared,\n", + " is set to 10 by default.\n", + "\n", + "calc_vol : positive scalar or None, optional\n", + " if the user specifies a diameter, the function will return the volume\n", + " occupied by the grain fraction up to that diameter.\n", + "\n", + "text_file : string or None, optional\n", + " if the user specifies a name, the function will store a csv file\n", + " with that name containing the Saltykov output.\n", + "\n", + "return_data : bool, optional\n", + " if True the function will return the position of the midpoints and\n", + " the frequencies.\n", + "\n", + "left_edge : positive scalar or 'min', optional\n", + " set the left edge of the histogram. Default is zero.\n", + "\n", + "Call functions\n", + "--------------\n", + "- unfold_population\n", + "- Saltykov_plot\n", + "\n", + "Examples\n", + "--------\n", + ">>> Saltykov(diameters)\n", + ">>> Saltykov(diameters, numbins=16, calc_vol=40)\n", + ">>> Saltykov(diameters, text_file='foo.csv')\n", + ">>> mid_points, frequencies = Saltykov(diameters, return_data=True)\n", + "\n", + "References\n", + "----------\n", + "Saltykov SA (1967) http://doi.org/10.1007/978-3-642-88260-9_31\n", + "Sahagian and Proussevitch (1998) https://doi.org/10.1016/S0377-0273(98)00043-2\n", + "\n", + "Return\n", + "------\n", + "Statistical descriptors, a plot, and/or a file with the data (optional)\n", + "\u001b[1;31mFile:\u001b[0m c:\\users\\marco\\documents\\github\\grainsizetools\\grain_size_tools\\stereology.py\n", + "\u001b[1;31mType:\u001b[0m function\n" + ], + "name": "stdout" } ], "source": [ @@ -227,12 +203,10 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ - "[1.31536871e-03 2.17302235e-02 2.25631643e-02 1.45570771e-02\n", - " 6.13586532e-03 2.24830266e-03 1.29306084e-03 3.60326809e-04\n", - " 0.00000000e+00 0.00000000e+00 4.11071036e-05]\n" + "[1.31536871e-03 2.17302235e-02 2.25631643e-02 1.45570771e-02\n 6.13586532e-03 2.24830266e-03 1.29306084e-03 3.60326809e-04\n 0.00000000e+00 0.00000000e+00 4.11071036e-05]\n" ] } ], @@ -254,14 +228,14 @@ "metadata": {}, "outputs": [ { + "output_type": "execute_result", "data": { "text/plain": [ "0.07024449636922886" ] }, - "execution_count": 7, "metadata": {}, - "output_type": "execute_result" + "execution_count": 7 } ], "source": [ @@ -281,14 +255,14 @@ "metadata": {}, "outputs": [ { + "output_type": "execute_result", "data": { "text/plain": [ "1.000000650312342" ] }, - "execution_count": 8, "metadata": {}, - "output_type": "execute_result" + "execution_count": 8 } ], "source": [ @@ -309,15 +283,15 @@ "metadata": {}, "outputs": [ { + "output_type": "execute_result", "data": { "text/plain": [ "array([ 1.87, 30.94, 32.12, 20.72, 8.74, 3.2 , 1.84, 0.51, 0. ,\n", " 0. , 0.06])" ] }, - "execution_count": 9, "metadata": {}, - "output_type": "execute_result" + "execution_count": 9 } ], "source": [ @@ -350,26 +324,20 @@ "metadata": {}, "outputs": [ { - "name": "stdout", "output_type": "stream", + "name": "stdout", "text": [ - "=======================================\n", - "PREDICTED OPTIMAL VALUES\n", - "Number of classes: 11\n", - "MSD (lognormal shape) = 1.63 ± 0.06\n", - "Geometric mean (scale) = 36.05 ± 1.27\n", - "=======================================\n" + "=======================================\nPREDICTED OPTIMAL VALUES\nNumber of classes: 11\nMSD (lognormal shape) = 1.63 ± 0.06\nGeometric mean (scale) = 36.05 ± 1.27\n=======================================\n" ] }, { + "output_type": "display_data", "data": { - "image/png": "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\n", - "text/plain": [ - "
" - ] + "text/plain": "
", + "image/svg+xml": "\r\n\r\n\r\n\r\n \r\n \r\n \r\n \r\n 2020-12-31T14:09:15.059631\r\n image/svg+xml\r\n \r\n \r\n Matplotlib v3.3.2, https://matplotlib.org/\r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n \r\n\r\n", + "image/png": "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\n" }, - "metadata": {}, - "output_type": "display_data" + "metadata": {} } ], "source": [ @@ -402,9 +370,9 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.7" + "version": "3.7.9-final" } }, "nbformat": 4, "nbformat_minor": 4 -} +} \ No newline at end of file