{"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":"# 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\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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"# Base class for classifier\nclass Classifier():\n  def __init__(self):\n    self.train = None\n    self.test = None \n    self.model = None\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  \n  def countvectorize(self):\n      tv = TfidfVectorizer(ngram_range=(1,3), token_pattern=r'\\w{1,}',\n               min_df=3, max_df=0.9, strip_accents='unicode', use_idf=1,\n               smooth_idf=1, sublinear_tf=1, max_features=5000)\n      # cv = CountVectorizer()\n      text = pd.concat([self.train.question_text, self.test.question_text])\n      tv.fit(text)\n      self.vector_train = tv.transform(self.train.question_text)\n      self.vector_test  = tv.transform(self.test.question_text)\n      logging.info(\"Train & test text tokenized\")\n\n  def build_model(self):\n      pass\n\n  def run_model(self):\n      # Choose your own classifier: self.model and run it\n      logging.info(f\"{self.__class__.__name__} starts running.\")\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=2090)\n      self.model.fit(x_train, y_train)\n      y_preds = self.model.predict(x_val)\n      logging.info(f\"Accuracy score: {accuracy_score(y_val, y_preds)}\")\n\n      y_preds = self.model.predict(self.vector_test)\n      return y_preds\n\n  def save_predictions(self, y_preds):\n      sub = pd.read_csv(f\"sample_submission.csv\")\n      sub['prediction'] = y_preds \n      sub.to_csv(f\"submission_{self.__class__.__name__}.csv\", index=False)\n      logging.info('Prediction exported to submisison.csv')\n  \n  def pipeline(self):\n      s_time = time.clock()\n      self.load_data()\n      self.countvectorize()\n      self.build_model()\n      self.save_predictions(self.run_model())\n      logging.info(f\"Program running for {time.clock() - s_time} seconds\")\n\nclass C_Bayes(Classifier):\n  def build_model(self):\n      self.model = MultinomialNB()\n      return self.model\n\n# Logistic Regression \nclass C_LR(Classifier):\n  def build_model(self):\n      self.model = LogisticRegression(n_jobs=10, solver='saga', C=0.1, verbose=1)\n      return self.model\n\nclass C_SVM(Classifier):\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.train = self.train.sample(10000)\n      self.test = pd.read_csv(test_file, engine='python', encoding='utf-8', error_bad_lines=False)\n      logging.info('CSV data loaded')\n\n  def build_model(self):\n      self.model = svm.SVC()\n      return self.model\n\nclass C_Ensemble(Classifier):\n  def ensemble(self):\n      s_time = time.perf_counter()\n      self.load_data()\n      self.countvectorize()\n\n      nb = MultinomialNB()\n      lr = LogisticRegression(n_jobs=10, solver='saga', C=0.1, verbose=1)\n      svc = svm.SVC()\n\n      all_preds = [0] * self.test.shape[0]\n      for m in (nb, lr, svc):\n          self.model = m\n          if m == svc: \n              self.load_data()\n              self.train = self.train.sample(10000)\n              self.countvectorize()\n          all_preds += self.run_model()\n      \n      all_preds = [1 if p > 0 else 0 for p in all_preds]\n      self.save_predictions(all_preds)\n      logging.info(f\"Program running for {time.perf_counter() - s_time} seconds\")\n\n  \nC_Ensemble().ensemble()     \n! cp submission_C_Ensemble.csv submission.csv","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def batch_nb():\n  all_preds = []\n  b = C_Bayes()\n  b.load_data()\n  full_train = b.train\n\n  for _ in range(10):\n    b.train = full_train.sample(1000000)\n    b.countvectorize()\n    b.build_model()\n    y_preds = b.run_model()\n    all_preds = all_preds + y_preds if len(all_preds) > 0 else y_preds\n\n  all_preds = [1 if p >=1  else 0 for p in all_preds]\n  b.save_predictions(all_preds)\n\n# batch_nb()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# ! cp submission_C_Bayes.csv submission.csv\n# ! ls\n","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}