{ "cells": [ { "cell_type": "markdown", "metadata": { "_cell_guid": "e5ef039d-bedd-e676-eb9c-a1d461d30637" }, "source": [ "test" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "b2bea244-509e-177d-b33e-1acaca42f30f" }, "outputs": [], "source": [ "" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "e8e5c6fc-539a-a639-5fb1-1d013a3b6308" }, "outputs": [], "source": [ "# coding: utf-8\n", "__author__ = 'Sandro Vega Pons : https://www.kaggle.com/svpons'\n", "\n", "'''Partially based on grid_plus_classifier script:\n", "https://www.kaggle.com/svpons/facebook-v-predicting-check-ins/grid-plus-classifier\n", "'''\n", "\n", "import numpy as np\n", "import pandas as pd\n", "from sklearn.preprocessing import LabelEncoder\n", "from sklearn.neighbors import KNeighborsClassifier\n", "\n", "\n", "def prepare_data(df, n_cell_x, n_cell_y):\n", " \"\"\"\n", " Feature engineering and computation of the grid.\n", " \"\"\"\n", " #Creating the grid\n", " size_x = 10. / n_cell_x\n", " size_y = 10. / n_cell_y\n", " eps = 0.00001 \n", " xs = np.where(df.x.values < eps, 0, df.x.values - eps)\n", " ys = np.where(df.y.values < eps, 0, df.y.values - eps)\n", " pos_x = (xs / size_x).astype(np.int)\n", " pos_y = (ys / size_y).astype(np.int)\n", " df['grid_cell'] = pos_y * n_cell_x + pos_x\n", " \n", " #Feature engineering\n", " fw = [500, 1000, 4, 3, 1./22., 2, 10] #feature weights (black magic here)\n", " df.x = df.x.values * fw[0]\n", " df.y = df.y.values * fw[1]\n", " initial_date = np.datetime64('2014-01-01T01:01', dtype='datetime64[m]') \n", " d_times = pd.DatetimeIndex(initial_date + np.timedelta64(int(mn), 'm') \n", " for mn in df.time.values) \n", " df['hour'] = d_times.hour * fw[2]\n", " df['weekday'] = d_times.weekday * fw[3]\n", " df['day'] = (d_times.dayofyear * fw[4]).astype(int)\n", " df['month'] = d_times.month * fw[5]\n", " df['year'] = (d_times.year - 2013) * fw[6]\n", "\n", " df = df.drop(['time'], axis=1) \n", " return df\n", " \n", "\n", "def process_one_cell(df_train, df_test, grid_id, th):\n", " \"\"\" \n", " Classification inside one grid cell.\n", " \"\"\" \n", " #Working on df_train\n", " df_cell_train = df_train.loc[df_train.grid_cell == grid_id]\n", " place_counts = df_cell_train.place_id.value_counts()\n", " mask = (place_counts[df_cell_train.place_id.values] >= th).values\n", " df_cell_train = df_cell_train.loc[mask]\n", "\n", " #Working on df_test\n", " df_cell_test = df_test.loc[df_test.grid_cell == grid_id]\n", " row_ids = df_cell_test.index\n", " \n", " #Preparing data\n", " le = LabelEncoder()\n", " y = le.fit_transform(df_cell_train.place_id.values)\n", " X = df_cell_train.drop(['place_id', 'grid_cell'], axis=1).values.astype(int)\n", " X_test = df_cell_test.drop(['grid_cell'], axis = 1).values.astype(int)\n", " \n", " #Applying the classifier\n", " clf = KNeighborsClassifier(n_neighbors=25, weights='distance', \n", " metric='manhattan')\n", " clf.fit(X, y)\n", " y_pred = clf.predict_proba(X_test)\n", " pred_labels = le.inverse_transform(np.argsort(y_pred, axis=1)[:,::-1][:,:3]) \n", " return pred_labels, row_ids\n", " \n", " \n", "def process_grid(df_train, df_test, th, n_cells):\n", " \"\"\"\n", " Iterates over all grid cells, aggregates the results and makes the\n", " submission.\n", " \"\"\" \n", " preds = np.zeros((df_test.shape[0], 3), dtype=int)\n", " \n", " for g_id in range(n_cells):\n", " if g_id % 100 == 0:\n", " print('iter: %s' %(g_id))\n", " \n", " #Applying classifier to one grid cell\n", " pred_labels, row_ids = process_one_cell(df_train, df_test, g_id, th)\n", "\n", " #Updating predictions\n", " preds[row_ids] = pred_labels\n", "\n", " print('Generating submission file ...')\n", " #Auxiliary dataframe with the 3 best predictions for each sample\n", " df_aux = pd.DataFrame(preds, dtype=str, columns=['l1', 'l2', 'l3']) \n", " \n", " #Concatenating the 3 predictions for each sample\n", " ds_sub = df_aux.l1.str.cat([df_aux.l2, df_aux.l3], sep=' ')\n", " \n", " #Writting to csv\n", " ds_sub.name = 'place_id'\n", " ds_sub.to_csv('sub_knn.csv', index=True, header=True, index_label='row_id') \n", " \n", "\n", "if __name__ == '__main__':\n", " \"\"\"\n", " \"\"\"\n", " print('Loading data ...')\n", " df_train = pd.read_csv('../input/train.csv',\n", " usecols=['row_id','x','y','time','place_id'], \n", " index_col = 0)\n", " df_test = pd.read_csv('../input/test.csv',\n", " usecols=['row_id','x','y','time'],\n", " index_col = 0)\n", " \n", " #Defining the size of the grid\n", " n_cell_x = 20\n", " n_cell_y = 40 \n", " \n", " print('Preparing train data')\n", " df_train = prepare_data(df_train, n_cell_x, n_cell_y)\n", " \n", " print('Preparing test data')\n", " df_test = prepare_data(df_test, n_cell_x, n_cell_y)\n", " \n", " #Solving classification problems inside each grid cell\n", " th = 5 #Keeping place_ids with more than th samples. \n", " process_grid(df_train, df_test, th, n_cell_x*n_cell_y)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "fe259944-cfb1-7b2a-a344-3b52d8c0a182" }, "outputs": [], "source": [ "" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "9d7e27c5-7ef6-03d8-e6fc-8d2d4c78904a" }, "outputs": [], "source": [ "" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "5592d9cf-daac-e846-82d2-bab69be0eca2" }, "outputs": [], "source": [ "" ] } ], "metadata": { "_change_revision": 0, "_is_fork": false, "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.5.2" } }, "nbformat": 4, "nbformat_minor": 0 }