{"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\n# Load packages \nimport math\nimport re\nimport os\nimport timeit\nimport tensorflow as tf\nimport numpy as np\nimport pandas as pd\nimport seaborn as sns\nimport matplotlib.pyplot as plt\nimport nltk\nimport logging\nimport time\n\nfrom sklearn import svm\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import accuracy_score, confusion_matrix, classification_report, f1_score\nfrom sklearn.naive_bayes import MultinomialNB\nfrom sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer\nlogging.basicConfig(format='[%(asctime)s %(levelname)8s] %(message)s', level=logging.INFO, datefmt='%m-%d %H:%M:%S')\n\n! cp ../input/quora-insincere-questions-classification/*.csv .","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class C_LR():\n  def __init__(self):\n    self.train = None\n    self.test = None \n    print(\"Class LR\")\n\n  def load_data(self, train_file='train.csv', test_file='test.csv'):\n      \"\"\" Load train, test csv files and return pandas.DataFrame\n      \"\"\"\n      self.train = pd.read_csv(train_file, engine='python', encoding='utf-8', error_bad_lines=False)\n      self.test = pd.read_csv(test_file, engine='python', encoding='utf-8', error_bad_lines=False)\n      logging.info('CSV data loaded')\n      print(\"...\")\n    \n    \n  def countvectorize(self):\n      tv = CountVectorizer()\n      tv.fit(self.train.question_text)\n      self.vector_train = tv.transform(self.train.question_text)\n      self.vector_test  = tv.transform(self.test.question_text)\n      print(\"Train & test text tokenized\")\n\n  def run_model(self):\n      nb = MultinomialNB()\n      labels = self.train.target\n      x_train, x_val, y_train, y_val = train_test_split(self.vector_train, labels, test_size=0.2, random_state=23)\n      nb.fit(x_train, y_train)\n      y_preds = nb.predict(x_val)\n      print(f\"Accuracy score: {accuracy_score(y_val, y_preds)}\")\n\n      y_preds = nb.predict_proba(self.vector_test)\n      return y_preds\n  \n  def save_predictions(self, y_preds):\n      sub = pd.read_csv('sample_submission.csv')\n      for i in range(len(y_preds)):\n        if len(self.test.iloc[i].question_text) <= 10:\n            y_preds[i] = 1\n                \n      sub['prediction'] = y_preds \n    \n      sub.to_csv('submission.csv', index=False)\n      print('Prediction exported to submisison.csv')\n\nlr = C_LR()\nlr.load_data()\n# b.train = b.train.sample(100000)\nlr.countvectorize()\nlabels = lr.train.target\nx_train, x_val, y_train, y_val = train_test_split(lr.vector_train, labels, test_size=0.2, random_state=2090)\n\nmodel = LogisticRegression(n_jobs=10, solver='saga', C=0.1, verbose=1)\nmodel.fit(x_train, y_train)\ny_preds = model.predict(x_val)\n\nprint(f\"Accuracy score: {accuracy_score(y_val, y_preds)}\")\nprint(f\"Confusion matrix: \") \nprint(confusion_matrix(y_val, y_preds))\nprint(\"Classificaiton report:\\n\", classification_report(y_val, y_preds, target_names=[\"Sincere\", \"Insincere\"]))\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_probs = model.predict_proba(x_val)\ny_probs\nbest_threshold = best_f1 = 0\n\nfor i in range(0, 100):\n  y2_preds = [1 if e[1] >= i / 100 else 0 for e in y_probs]\n  cur_f1 = f1_score(y_val, y2_preds)\n  print(i, cur_f1)\n  if cur_f1 > best_f1:\n    best_f1 = cur_f1\n    best_threshold = i / 100\n\nprint(f\"Best f1 score {best_f1}, best threshold {best_threshold}\")\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"y_probs = model.predict_proba(x_val)\ny_probs\ny2_preds = [1 if e[1] >= 0.25 else 0 for e in y_probs]\n\nprint(f\"Confusion matrix: \") \nprint(confusion_matrix(y_val, y2_preds))\nprint(\"Classificaiton report:\\n\", classification_report(y_val, y2_preds, target_names=[\"Sincere\", \"Insincere\"]))\n\ntest_proba = model.predict_proba(lr.vector_test)\ntest_preds = [1 if e[1] >= 0.19 else 0 for e in test_proba]\nsub = pd.read_csv(f\"sample_submission.csv\")\nsub['prediction'] = test_preds\nsub.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!head -n 10 submission.csv","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}