diff --git a/HW1_R10631036/HW1_R10631036.ipynb b/HW1_R10631036/HW1_R10631036.ipynb new file mode 100644 index 0000000..bc5a6f9 --- /dev/null +++ b/HW1_R10631036/HW1_R10631036.ipynb @@ -0,0 +1 @@ +{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"HW1_R10631036.ipynb","provenance":[],"collapsed_sections":[],"authorship_tag":"ABX9TyOsUhFTdgiiW8RVaGR7DeN+"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"}},"cells":[{"cell_type":"code","source":["from google.colab import drive\n","drive.mount('/content/drive')"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"SDqvyuFwultw","executionInfo":{"status":"ok","timestamp":1657184768121,"user_tz":-480,"elapsed":22146,"user":{"displayName":"許伯豪","userId":"04905258514356166770"}},"outputId":"b7fa6d8f-d79f-471b-c95c-23bd5136786b"},"execution_count":4,"outputs":[{"output_type":"stream","name":"stdout","text":["Mounted at /content/drive\n"]}]},{"cell_type":"code","source":["raw_path = '/content/drive/MyDrive/Bioimformatic algorithem/week1/2022summer-git-python_basics/HW1'\n","data = '/HW1.txt'\n"],"metadata":{"id":"bQ5GuPyrupxW","executionInfo":{"status":"ok","timestamp":1657184769315,"user_tz":-480,"elapsed":6,"user":{"displayName":"許伯豪","userId":"04905258514356166770"}}},"execution_count":5,"outputs":[]},{"cell_type":"code","source":["count = 0\n","random_noise = '!?+-'\n","without_noise = 0\n","with open(raw_path+data, 'r') as f:\n"," for i in f:\n"," count += 1\n"," if (random_noise in i):\n"," without_noise += 1\n"," continue\n"," print('total number of sentences is %d' % count)\n"," print('total number of sentences without noise is %d' % without_noise)\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"9kxLLbxzxcUT","executionInfo":{"status":"ok","timestamp":1657197483172,"user_tz":-480,"elapsed":280,"user":{"displayName":"許伯豪","userId":"04905258514356166770"}},"outputId":"ea5ac619-ccff-4d10-d729-9dc97bf89166"},"execution_count":59,"outputs":[{"output_type":"stream","name":"stdout","text":["total number of sentences is 539\n","total number of sentences without noise is 21\n"]}]},{"cell_type":"code","source":["def lensort(len_dic, i):\n"," if len(i) <= 40:\n"," len_dic['<=40'] += 1\n"," elif 40 < len(i) <= 50:\n"," len_dic['<=50'] += 1\n"," elif 50 < len(i) <= 60:\n"," len_dic['<=60'] += 1\n"," elif 60 < len(i) <= 70:\n"," len_dic['<=70'] += 1\n"," elif 70 < len(i) <= 80:\n"," len_dic['<=80'] += 1 \n"," elif len(i) > 80:\n"," len_dic['>80'] += 1\n"," return len_dic"],"metadata":{"id":"NVI47_0Fgzlk","executionInfo":{"status":"ok","timestamp":1657195610591,"user_tz":-480,"elapsed":314,"user":{"displayName":"許伯豪","userId":"04905258514356166770"}}},"execution_count":52,"outputs":[]},{"cell_type":"code","source":["count = 0\n","random_noise = '!?+-'\n","without_noise = 0\n","len_dic_before = {'<=40':0, '<=50':0, '<=60':0, '<=70':0, '<=80':0, '>80':0}\n","len_dic_after = {'<=40':0, '<=50':0, '<=60':0, '<=70':0, '<=80':0, '>80':0}\n","with open(raw_path+data, 'r') as f:\n"," for i in f:\n"," len_dic_before = lensort(len_dic_before, i)\n","with open(raw_path+data, 'r') as f:\n"," for i in f:\n"," if (random_noise not in i):\n"," len_dic_after = lensort(len_dic_after, i)\n","\n","with open(raw_path+data, 'r') as f:\n"," for i in f:\n"," if (random_noise in i):\n"," for a in i:\n"," if (a in random_noise):\n"," i=i.replace(a, '')\n"," len_dic_after = lensort(len_dic_after, i)\n"," \n"," \n"],"metadata":{"id":"IoLU_w_p9cQa","executionInfo":{"status":"ok","timestamp":1657195613133,"user_tz":-480,"elapsed":345,"user":{"displayName":"許伯豪","userId":"04905258514356166770"}}},"execution_count":53,"outputs":[]},{"cell_type":"code","source":["with open('/content/drive/MyDrive/Bioimformatic algorithem/week1/2022summer-git-python_basics/HW1_R10631036/HW1_R10631036.txt', 'w')as f:\n"," f.write('There are {} sentences in HW1.txt. {} of them include !?+-.'.format(count,without_noise)+'\\n')\n"," f.write('{} {} {}'.format('length', 'before trim', 'after trim')+'\\n')\n"," for i in len_dic_after.keys():\n"," f.write('{0:>6}{1:>12}{2:>11}'.format(i, len_dic_before['%s'%i], len_dic_after['%s'%i])+'\\n')"],"metadata":{"id":"r6Oxbh5lnlTn","executionInfo":{"status":"ok","timestamp":1657201909181,"user_tz":-480,"elapsed":288,"user":{"displayName":"許伯豪","userId":"04905258514356166770"}}},"execution_count":100,"outputs":[]}]} \ No newline at end of file diff --git a/HW1_R10631036/HW1_R10631036.txt b/HW1_R10631036/HW1_R10631036.txt new file mode 100644 index 0000000..5bef2ec --- /dev/null +++ b/HW1_R10631036/HW1_R10631036.txt @@ -0,0 +1,8 @@ +There are 539 sentences in HW1.txt. 21 of them include !?+-. +length before trim after trim + <=40 27 28 + <=50 161 164 + <=60 156 155 + <=70 121 121 + <=80 61 60 + >80 13 11 diff --git a/python_basics/0705.txt b/python_basics/0705.txt new file mode 100644 index 0000000..079f188 --- /dev/null +++ b/python_basics/0705.txt @@ -0,0 +1 @@ +push test diff --git a/python_basics/name.txt b/python_basics/name.txt new file mode 100644 index 0000000..e1216ff --- /dev/null +++ b/python_basics/name.txt @@ -0,0 +1 @@ +my name is BaronHsu