Docs.

felixleopoldo · Dec 6, 2023 · 97701d7 · 97701d7
1 parent ba7a1e2
commit 97701d7
Show file tree

Hide file tree

Showing 11 changed files with 200 additions and 170 deletions.
diff --git a/docs/source/fig1_demo.ipynb b/docs/source/fig1_demo.ipynb
@@ -659,7 +659,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "You main also plot the minimal CSI relations as below. See the paper for definition of a minimal CSI."
+    "You may also plot the minimal CSI relations as below. See the paper for definition of a minimal CSI."
    ]
   },
   {
@@ -939,7 +939,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Data sampled from a CStree is stored as a Pandas dataframe, with labels inherited from the CStree level labels. The second row shows the cardinalities of variables."
+    "Data sampled from a CStree is stored as a Pandas dataframe, with labels inherited from the CStree level labels. The second row contains the cardinalities of variables."
    ]
   },
   {
@@ -1281,7 +1281,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "You may easily read a CStree from a Pandas dataframe. Norte that CStrees can thus be saved to file as a usual Pandas dataframe."
+    "You may easily read a CStree from a Pandas dataframe. A CStree can thus be saved to file as a usual Pandas dataframe."
    ]
   },
   {

diff --git a/docs/source/learn_demo.ipynb b/docs/source/learn_demo.ipynb
@@ -12,7 +12,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "This notebook shows how to learn a CStree from observational data using exhaustive search. "
+    "This notebook shows how to learn a CStree from observational data using an exhaustive search. procedure. "
    ]
   },
   {
@@ -442,7 +442,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Both the structure learning (learning of CStree) and the parameter estimation, use pre-calculated scores. We restrict the number of variables in each context to be at most 2 and use the BDeu score with pseudo count 1. By letting poss_cvars=None, the possible context variables for a variable are unrestricted."
+    "The structure learning (learning of CStree) uses pre-calculated scores. We restrict the number of variables in each context to be at most 2 and use the BDeu score with pseudo count 1. By letting poss_cvars=None, the possible context variables for a variable are unrestricted."
    ]
   },
   {
@@ -470,7 +470,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Th dict score_table contains the order score tables and context_scores, the scores for every context of every variable. "
+    "The dict score_table contains the order score tables and context_scores, the scores for every context of every variable. "
    ]
   },
   {
@@ -799,7 +799,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Estimate the stage parameters using the BDeu prior with total pseudo count 1."
+    "Estimate the stage parameters using the BDeu prior with a total pseudo count per level of 1."
    ]
   },
   {

diff --git a/docs/source/learn_demo_gibbs.ipynb b/docs/source/learn_demo_gibbs.ipynb
@@ -11,7 +11,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "This notebook shows how to learn a CStree from observational data using McMC (Gibbs) sampling from the posterior order distribution. "
+    "This notebook shows how to learn a CStree from observational data using McMC (Gibbs) sampling to approximate the posterior order distribution. "
    ]
   },
   {
@@ -1170,28 +1170,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 80,
+   "execution_count": 94,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Depth=1, working on node 3: 100%|██████████| 4/4 [00:00<00:00, 4277.72it/s]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Depth=1, working on node 3: 100%|██████████| 4/4 [00:00<00:00, 1642.57it/s]"
+      "Depth=1, working on node 3: 100%|██████████| 4/4 [00:00<00:00, 1812.38it/s]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Possible context vararibles per node: {'a': [], 'b': ['d'], 'c': ['d'], 'd': ['b', 'c']}\n"
+      "Possible context variables per node: {'a': [], 'b': ['d'], 'c': ['d'], 'd': ['b', 'c']}\n"
      ]
     },
     {
@@ -1205,7 +1198,7 @@
    "source": [
     "pcgraph = pc(x[1:].values, 0.05, \"chisq\", node_names=x.columns)\n",
     "poss_cvars = ctl.causallearn_graph_to_posscvars(pcgraph, labels=x.columns)\n",
-    "print(\"Possible context vararibles per node:\", poss_cvars)"
+    "print(\"Possible context variables per node:\", poss_cvars)"
    ]
   },
   {
@@ -1280,7 +1273,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "We plot the first 200 interations of the order score trajectory."
+    "We plot the first 200 iterations of the order score trajectory."
    ]
   },
   {
@@ -1314,7 +1307,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "To further investigate the McMC trajectory we find the individual variables positions/levels in the orders and plot these. This gives an overview of the mixing properties of the sampler and if the trjaectory seems to have converged."
+    "To further investigate the McMC trajectory we find the individual variables positions/levels in the orders and plot these. This gives an overview of the mixing properties of the sampler and if the trajectory seems to have converged."
    ]
   },
   {
@@ -1332,7 +1325,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Assuming that the majority of praobability mass will center around the order corresponding to the true CStree (though there could be many or them), the a-line should converge to 0 (i.e. position 0), the b-line should converge to 1, and so on."
+    "Assuming that the majority of probability mass is centered around the order corresponding to the true CStree (though there could be many or them), the a-line should converge to 0 (i.e. position 0), the b-line should converge to 1, and so on."
    ]
   },
   {

diff --git a/notebooks/fig1_demo.ipynb b/notebooks/fig1_demo.ipynb
@@ -659,7 +659,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "You main also plot the minimal CSI relations as below. See the paper for definition of a minimal CSI."
+    "You may also plot the minimal CSI relations as below. See the paper for definition of a minimal CSI."
    ]
   },
   {
@@ -939,7 +939,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Data sampled from a CStree is stored as a Pandas dataframe, with labels inherited from the CStree level labels. The second row shows the cardinalities of variables."
+    "Data sampled from a CStree is stored as a Pandas dataframe, with labels inherited from the CStree level labels. The second row contains the cardinalities of variables."
    ]
   },
   {
@@ -1281,7 +1281,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "You may easily read a CStree from a Pandas dataframe. Norte that CStrees can thus be saved to file as a usual Pandas dataframe."
+    "You may easily read a CStree from a Pandas dataframe. A CStree can thus be saved to file as a usual Pandas dataframe."
    ]
   },
   {

diff --git a/notebooks/learn_demo.ipynb b/notebooks/learn_demo.ipynb
@@ -12,7 +12,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "This notebook shows how to learn a CStree from observational data using exhaustive search. "
+    "This notebook shows how to learn a CStree from observational data using an exhaustive search. procedure. "
    ]
   },
   {
@@ -442,7 +442,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Both the structure learning (learning of CStree) and the parameter estimation, use pre-calculated scores. We restrict the number of variables in each context to be at most 2 and use the BDeu score with pseudo count 1. By letting poss_cvars=None, the possible context variables for a variable are unrestricted."
+    "The structure learning (learning of CStree) uses pre-calculated scores. We restrict the number of variables in each context to be at most 2 and use the BDeu score with pseudo count 1. By letting poss_cvars=None, the possible context variables for a variable are unrestricted."
    ]
   },
   {
@@ -470,7 +470,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Th dict score_table contains the order score tables and context_scores, the scores for every context of every variable. "
+    "The dict score_table contains the order score tables and context_scores, the scores for every context of every variable. "
    ]
   },
   {
@@ -799,7 +799,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Estimate the stage parameters using the BDeu prior with total pseudo count 1."
+    "Estimate the stage parameters using the BDeu prior with a total pseudo count per level of 1."
    ]
   },
   {

diff --git a/notebooks/learn_demo_gibbs.ipynb b/notebooks/learn_demo_gibbs.ipynb
@@ -11,7 +11,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "This notebook shows how to learn a CStree from observational data using McMC (Gibbs) sampling from the posterior order distribution. "
+    "This notebook shows how to learn a CStree from observational data using McMC (Gibbs) sampling to approximate the posterior order distribution. "
    ]
   },
   {
@@ -1170,28 +1170,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 80,
+   "execution_count": 94,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Depth=1, working on node 3: 100%|██████████| 4/4 [00:00<00:00, 4277.72it/s]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Depth=1, working on node 3: 100%|██████████| 4/4 [00:00<00:00, 1642.57it/s]"
+      "Depth=1, working on node 3: 100%|██████████| 4/4 [00:00<00:00, 1812.38it/s]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Possible context vararibles per node: {'a': [], 'b': ['d'], 'c': ['d'], 'd': ['b', 'c']}\n"
+      "Possible context variables per node: {'a': [], 'b': ['d'], 'c': ['d'], 'd': ['b', 'c']}\n"
      ]
     },
     {
@@ -1205,7 +1198,7 @@
    "source": [
     "pcgraph = pc(x[1:].values, 0.05, \"chisq\", node_names=x.columns)\n",
     "poss_cvars = ctl.causallearn_graph_to_posscvars(pcgraph, labels=x.columns)\n",
-    "print(\"Possible context vararibles per node:\", poss_cvars)"
+    "print(\"Possible context variables per node:\", poss_cvars)"
    ]
   },
   {
@@ -1280,7 +1273,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "We plot the first 200 interations of the order score trajectory."
+    "We plot the first 200 iterations of the order score trajectory."
    ]
   },
   {
@@ -1314,7 +1307,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "To further investigate the McMC trajectory we find the individual variables positions/levels in the orders and plot these. This gives an overview of the mixing properties of the sampler and if the trjaectory seems to have converged."
+    "To further investigate the McMC trajectory we find the individual variables positions/levels in the orders and plot these. This gives an overview of the mixing properties of the sampler and if the trajectory seems to have converged."
    ]
   },
   {
@@ -1332,7 +1325,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Assuming that the majority of praobability mass will center around the order corresponding to the true CStree (though there could be many or them), the a-line should converge to 0 (i.e. position 0), the b-line should converge to 1, and so on."
+    "Assuming that the majority of probability mass is centered around the order corresponding to the true CStree (though there could be many or them), the a-line should converge to 0 (i.e. position 0), the b-line should converge to 1, and so on."
    ]
   },
   {