{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport pandas as pd\nimport numpy as np\nimport spacy\nfrom tensorflow import keras\nfrom sklearn.feature_extraction.text import CountVectorizer\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.linear_model import LogisticRegressionCV\nfrom sklearn.tree import DecisionTreeClassifier\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\ndata = pd.read_csv(\"../input/train.csv\",header=None,low_memory=False)\ndata_test = pd.read_csv(\"../input/test.csv\",header=None,low_memory=False)\nsentences = data[1][1:]\nsentences_test = data_test[1][1:]\nX = sentences.values\nY = data[2][1:]\nY = Y.values\nglove_model = spacy.load('en_core_web_lg')\nglove_model.remove_pipe('ner')\nglove_model.max_length = 93621305\n\nY = data[2][1:]\nY = Y.values\nsentences = data[1][1:]\n\n\ninsincere = X[Y == '1']\nsincere = X [Y == '0']\na = []\ny = []\nfor sent in insincere:\n    a.append(glove_model(sent).vector)\n    y.append(1)\nfor sent in sincere[:64674*4]:\n    a.append(glove_model(sent).vector)\n    y.append(0)\n\n\n\nLR_model = LogisticRegressionCV(cv=5,random_state=0, solver='lbfgs').fit(a, y)\ntree_model = DecisionTreeClassifier().fit(a,y)\n\n    \nX_test = []\nfor a in sentences_test:    \n    X_test.append(glove_model(a).vector)\n\npreds = tree_model.predict(X_test)\npreds = [int(x) for x in preds]\nsub = pd.read_csv(\"../input/sample_submission.csv\")\nsub[\"prediction\"] = preds\nsub.to_csv(\"submission.csv\",index=False)\n\n#import os\n#print(os.listdir(\"../input\"))","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","collapsed":true,"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":false},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}