{"cells":[{"metadata":{"_uuid":"aec3610bd14c775cc4a83838e3b6be27a7913a27"},"cell_type":"markdown","source":"![](https://scontent-frx5-1.cdninstagram.com/vp/934e9cd6cb4317e341a01209ce1b943a/5C70B12A/t51.2885-15/fr/e15/s1080x1080/38041281_264026917527878_172239497218490368_n.jpg?ig_cache_key=MTg0MDA2NjkxODU5ODcyMzQ5MA%3D%3D.2)"},{"metadata":{"trusted":true,"_uuid":"04410d2c16645c40e91aa280040e456904eb761f"},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\n\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.feature_extraction.text import TfidfVectorizer","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"train_df = pd.read_csv(\"../input/train.csv\", nrows=100000)\ntrain_txt = train_df[\"question_text\"]\n\ntest_df = pd.read_csv(\"../input/test.csv\")\ntest_txt = test_df[\"question_text\"]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"d73391a1219a6b692feabef18cdc585ad40f54d1"},"cell_type":"code","source":"# Feature extraction\ntfidf = TfidfVectorizer(\n    min_df=5, max_features=10000, strip_accents='unicode',lowercase =True,\n    analyzer='word', token_pattern=r'\\w+', ngram_range=(1, 3), use_idf=True, \n    smooth_idf=True, sublinear_tf=True, stop_words = 'english'\n).fit(train_txt)\n\nX_tr = tfidf.transform(train_txt)\nX_te = tfidf.transform(test_txt)\ny = train_df[\"target\"]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ebab38326d99986c6803951293e90168ae33b410"},"cell_type":"code","source":"# Classification and prediction\nclf = LogisticRegression(C=3)\nclf.fit(X_tr, y)\n\np_test = clf.predict_proba(X_te)[:, 0]\ny_te = (p_test > 0.5).astype(np.int)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"221ad851c0aec189222f58c5432d2326a8824c4f"},"cell_type":"code","source":"submit_df = pd.DataFrame({\"qid\": test_df[\"qid\"], \"prediction\": y_te})\nsubmit_df.to_csv(\"submission.csv\", index=False)","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}