{ "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "9ac07922-be35-55c9-02b7-ca02b67376ae" }, "outputs": [], "source": [ "# Garima and Ghaida Notebook kaggle decal Fall 2016\n", "# 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 in \n", "\n", "import numpy as np # linear algebra\n", "import pandas as pd \n", "# data processing, CSV file I/O (e.g. pd.read_csv)\n", "\n", "# Input data files are available in the \"../input/\" directory.\n", "# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n", "\n", "from subprocess import check_output\n", "print(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\n", "\n", "# Any results you write to the current directory are saved as output.\n", "import os\n", "import matplotlib.pyplot as plt\n", "from scipy.stats import gaussian_kde\n", "import time\n", "import seaborn as sns \n", "%matplotlib inline" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "7fe8d93d-29b5-b33b-2aea-5dc719177777" }, "outputs": [], "source": [ "df_train = pd.read_csv(\"../input/train.csv\")\n", "df_test = pd.read_csv(\"../input/test.csv\")\n", "df_train.head()\n", "\n", "df_train_sample = df_train.sample(n=150000)\n", "df_test_sample = df_test.sample(n=150000)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "70ce26c2-6f5d-d97b-b811-b0f70aabef33" }, "outputs": [], "source": [ "counts1, bins1 = np.histogram(df_train[\"accuracy\"], bins=50)\n", "binsc1 = bins1[:-1] + np.diff(bins1)/2.\n", "\n", "counts2, bins2 = np.histogram(df_test[\"accuracy\"], bins=50)\n", "binsc2 = bins2[:-1] + np.diff(bins2)/2.\n", "\n", "plt.figure(0, figsize=(14,4))\n", "\n", "plt.subplot(121)\n", "plt.bar(binsc1, counts1/(counts1.sum()*1.0), width=np.diff(bins1)[0])\n", "plt.grid(True)\n", "plt.xlabel(\"Accuracy\")\n", "plt.ylabel(\"Fraction\")\n", "plt.title(\"Train\")\n", "\n", "plt.subplot(122)\n", "plt.bar(binsc2, counts2/(counts2.sum()*1.0), width=np.diff(bins2)[0])\n", "plt.grid(True)\n", "plt.xlabel(\"Accuracy\")\n", "plt.ylabel(\"Fraction\")\n", "plt.title(\"Test\")\n", "\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "4e3dcff5-6fc1-083e-df8f-8f64a279e1f4" }, "outputs": [], "source": [ "import datetime\n", "from heapq import nlargest\n", "from operator import itemgetter\n", "import os\n", "import time\n", "import math\n", "from collections import defaultdict\n", "\n", "\n", "def prep_xy(x, y):\n", " range = 800\n", " ix = math.floor(range*x/10)\n", " if ix < 0:\n", " ix = 0\n", " if ix >= range:\n", " ix = range-1\n", "\n", " iy = math.floor(range*y/10)\n", " if iy < 0:\n", " iy = 0\n", " if iy >= range:\n", " iy = range-1\n", "\n", " return ix, iy\n", "\n", "\n", "def run_solution():\n", " print('Preparing data...')\n", " f = open(\"../input/train.csv\", \"r\")\n", " f.readline()\n", " total = 0\n", "\n", " grid = defaultdict(lambda: defaultdict(int))\n", " grid_sorted = dict()\n", "\n", " # Calc counts\n", " while 1:\n", " line = f.readline().strip()\n", " total += 1\n", "\n", " if line == '':\n", " break\n", "\n", " arr = line.split(\",\")\n", " row_id = arr[0]\n", " x = float(arr[1])\n", " y = float(arr[2])\n", " accuracy = arr[3]\n", " time = arr[4]\n", " place_id = arr[5]\n", "\n", " ix, iy = prep_xy(x, y)\n", "\n", " grid[(ix, iy)][place_id] += 1\n", "\n", " f.close()\n", "\n", " # Sort array\n", " for el in grid:\n", " grid_sorted[el] = nlargest(3, sorted(grid[el].items()), key=itemgetter(1))\n", "\n", " print('Generate submission...')\n", " sub_file = os.path.join('submission_' + str(datetime.datetime.now().strftime(\"%Y-%m-%d-%H-%M\")) + '.csv')\n", " out = open(sub_file, \"w\")\n", " f = open(\"../input/test.csv\", \"r\")\n", " f.readline()\n", " total = 0\n", " out.write(\"row_id,place_id\\n\")\n", "\n", " while 1:\n", " line = f.readline().strip()\n", " total += 1\n", "\n", " if line == '':\n", " break\n", "\n", " arr = line.split(\",\")\n", " row_id = arr[0]\n", " x = float(arr[1])\n", " y = float(arr[2])\n", " accuracy = arr[3]\n", " time = arr[4]\n", "\n", " out.write(str(row_id) + ',')\n", " filled = []\n", "\n", " ix, iy = prep_xy(x, y)\n", "\n", " s1 = (ix, iy)\n", " if s1 in grid_sorted:\n", " topitems = grid_sorted[s1]\n", " for i in range(len(topitems)):\n", " if topitems[i][0] in filled:\n", " continue\n", " if len(filled) == 3:\n", " break\n", " out.write(' ' + topitems[i][0])\n", " filled.append(topitems[i][0])\n", "\n", " out.write(\"\\n\")\n", "\n", " out.close()\n", " f.close()\n", "\n", "\n", "start_time = time.time()\n", "run_solution()\n", "print(\"Elapsed time overall: %s seconds\" % (time.time() - start_time))\n" ] } ], "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 }