{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport re\nimport string\nfrom sklearn.model_selection import train_test_split\nfrom sklearn import metrics\nimport nltk\nimport os\nimport gc\nfrom keras.preprocessing import sequence,text\nfrom keras.preprocessing.text import Tokenizer\nfrom keras.models import Sequential\nfrom keras.layers import Input, Dense,Dropout,Embedding,LSTM, CuDNNGRU, Conv1D,GlobalMaxPooling1D,Flatten,MaxPooling1D,GRU,GlobalMaxPool1D,SpatialDropout1D,Bidirectional\nfrom keras.callbacks import EarlyStopping\nfrom keras.utils import to_categorical\nfrom keras.models import Model\nfrom keras import initializers, regularizers, constraints, optimizers, layers\nfrom keras.losses import categorical_crossentropy\nfrom keras.optimizers import Adam\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import accuracy_score,confusion_matrix,classification_report,f1_score\nimport matplotlib.pyplot as plt\nimport warnings\nwarnings.filterwarnings(\"ignore\")\n\ntest = pd.read_csv(\"../input/test.csv\")\ntrain = pd.read_csv(\"../input/train.csv\")","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"ad26d362be253a83a5c7ad7cf2b3921a9d86847c"},"cell_type":"markdown","source":"## Text cleaning"},{"metadata":{"trusted":true,"_uuid":"ff4ad5e85a7e049d1b110016922779c43d7236dd"},"cell_type":"code","source":"from nltk.corpus import stopwords\nimport string\npunctuations = string.punctuation\nstopword = stopwords.words(\"english\")\ndef clean(text):\n    \n    lower_text = text.lower()\n    \n    text = \"\".join(w for w in lower_text if w not in punctuations)\n    \n    words = text.split()\n    words = [w for w in words if w not in stopword]\n    res = \" \".join(words)\n    return res\nclean(\"this is a test!\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"dc725ffbb22e3bc433e658a66f461dd75295059b"},"cell_type":"code","source":"\ntrain['cleaned'] = train['question_text'].apply(clean)\ntest['cleaned'] = test['question_text'].apply(clean)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"149cf15612f7d451deeee4f47f58a3522d873139"},"cell_type":"code","source":"from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer\n\ncvz = CountVectorizer()\nword_tfidf = TfidfVectorizer()\ncvz.fit(train[\"cleaned\"].values)\ncount_vector_train = cvz.transform(train[\"cleaned\"].values)\ncount_vector_test = cvz.transform(test[\"cleaned\"].values)\n\nword_tfidf.fit(train[\"cleaned\"].values)\nword_vector_train = word_tfidf.transform(train[\"cleaned\"].values)\nword_vector_test = word_tfidf.transform(test[\"cleaned\"].values)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2e93cbf05b8d51ddf705470d857cc60d9b19e0c9"},"cell_type":"code","source":"train_vector = word_vector_train\ntest_vector = word_vector_test\ntarget = train['target']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"45294d980fb83f014a76d929ae842c69569ac665"},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\ntrainx, valx, trainy, valy = train_test_split(train_vector,target)\n\nfrom imblearn.over_sampling import RandomOverSampler\nros = RandomOverSampler(random_state=777)\nX_ROS, y_ROS = ros.fit_sample(trainx, trainy)\n#X_ROS = trainx\n#y_ROS = trainy","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"4f8b766fcad3e5ec9c213a4885a8d8fe026d8590"},"cell_type":"code","source":"from sklearn import naive_bayes\nfrom sklearn import svm\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn import ensemble\nfrom sklearn.metrics import accuracy_score, f1_score","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ec09713ebab88cc76b863771b537e84adb20de1d"},"cell_type":"code","source":"model_1 = naive_bayes.MultinomialNB()\nmodel_1.fit(trainx,trainy)\npred1 = model_1.predict(valx)\nprint(accuracy_score(pred1,valy))\nprint(f1_score(pred1,valy))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"f9e16bd95e9d7eff3d0f3867c4c4903c143a2048"},"cell_type":"code","source":"model_2 = svm.SVC()\nmodel_2.fit(trainx,trainy)\npred2 = model_2.predict(valx)\nprint(accuracy_score(pred2,valy))\nprint(f1_score(pred2,valy))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"8188d6ce75332bfaeabaa56d2938c32dff18cc55"},"cell_type":"code","source":"model_3 = LogisticRegression()\nmodel_3.fit(trainx,trainy)\npred3 = model_3.predict(valx)\nprint(accuracy_score(pred3,valy))\nprint(f1_score(pred3,valy))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ab93555a036c7c92e5beb5a1c85229e6fe42ff2e"},"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}