{"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":{"trusted":true},"cell_type":"code","source":"import pandas as pd\n\ntrain = pd.read_csv('/kaggle/input/quora-insincere-questions-classification/train.csv')\ntest = pd.read_csv('/kaggle/input/quora-insincere-questions-classification/test.csv')\nsample_submission = pd.read_csv('/kaggle/input/quora-insincere-questions-classification/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = train['question_text']\ny = train['target'] ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# X_words = [i.split() for i in X]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# unique_words = set()\n\n# for li in X_words:\n#     for i in li:\n#         if i not in unique_words:\n#             unique_words.add(i)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# from nltk import word_tokenize\n\n# X_word_tokenized = list()\n\n# for que in X:\n#     X_word_tokenized.append(word_tokenize(que))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.02, random_state=41)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.feature_extraction.text import TfidfVectorizer\n\ntf=TfidfVectorizer()\ntrain_tf= tf.fit_transform(X_train)\ntest_tf= tf.transform(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# from sklearn.neighbors import KNeighborsClassifier\n\n# model = KNeighborsClassifier(n_neighbors=3)\n\n# # Train the model using the training sets\n# model.fit(train_tf,y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# #Predict Output\n# predicted_y = model.predict(test_tf)\n# model.score(predicted_y,y_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# from sklearn.tree import DecisionTreeClassifier\n\n# clf = DecisionTreeClassifier(random_state=0)\n# clf.fit(train_tf,y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# predicted_y = clf.predict(test_tf)\n# model.score(predicted_y,y_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.svm import LinearSVC\n\n# Create the LinearSVC model\nmodel = LinearSVC(random_state=1, dual=False)\n# Fit the model\nmodel.fit(train_tf, y_train)\n\n# Uncomment and run to see model accuracya\nprint(f'Model test accuracy: {model.score(test_tf, y_test)*100:.3f}%')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Validation","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"X_val = test['question_text']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"val_tf= tf.transform(X_val)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred = model.predict(val_tf)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission['prediction'] = pred","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission.to_csv('submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}