{"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\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"data = pd.read_csv('/kaggle/input/quora-insincere-questions-classification/train.csv')\ndata.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub_data = data.sample(100000)\nsub_data.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.feature_extraction.text import CountVectorizer\nfrom sklearn.model_selection import train_test_split\n\nsub_data['question_text'] = sub_data['question_text'].str.lower().str.replace('[^a-z\\s]', '')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_x, test_x, train_y, test_y = train_test_split(sub_data[['question_text']],\n                                                    sub_data['target'],\n                                                   test_size=0.2, random_state=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_x","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_x.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# min_df: only those terms whose total frequency is greater than 10 will be picked\nimport nltk\nstopwords = nltk.corpus.stopwords.words('english')\nstopwords.extend(['app', 'mobile', 'get', 'would', 'best'])\nvectorizer = CountVectorizer(min_df=10, stop_words=stopwords).fit(train_x['question_text'])\ntrain_dtm = vectorizer.transform(train_x['question_text'])\ntest_dtm = vectorizer.transform(test_x['question_text'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train_dtm = pd.DataFrame(train_dtm.toarray(), columns=vectorizer.get_feature_names())\ndf_test_dtm = pd.DataFrame(test_dtm.toarray(), columns=vectorizer.get_feature_names())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras import layers\nfrom tensorflow.keras.models import Sequential\nmodel = Sequential()\nmodel.add(layers.Dense(units=64, input_shape=(df_train_dtm.shape[1],), activation='relu'))\nmodel.add(layers.Dense(units=1, activation='sigmoid'))\nmodel.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])\nhistory = model.fit(df_train_dtm, train_y, validation_split=0.2, epochs=5, batch_size=1024, verbose=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\nplt.plot(history.history['val_loss'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_class = model.predict_classes(df_test_dtm.values)\nfrom sklearn.metrics import accuracy_score\naccuracy_score(test_y, pred_class)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}