{"cells": [{"metadata": {"_cell_guid": "7d1ce7cc-23ee-4096-9573-9d0e760e4623", "scrolled": true, "_uuid": "b7536a36b744a24f5a4171abc36f4459acae4c57"}, "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 in \n", "\n", "import numpy as np # linear algebra\n", "import pandas as pd # 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", "dataset=pd.read_csv(\"../input/train.csv\")\n", "from subprocess import check_output\n", "print(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\n", "\n", "X=dataset.iloc[:,1:785].values\n", "y=dataset.iloc[:,0:1].values\n", "\n", "\n", "\n", "\n", "from sklearn.cross_validation import train_test_split\n", "X_train1,X_valid1,y_train,y_valid=train_test_split(X,y,test_size=0.2)\n", "\n", "\n", "\n", "# Any results you write to the current directory are saved as output."], "execution_count": null, "cell_type": "code", "outputs": []}, {"metadata": {"_cell_guid": "39014260-ce4d-47fa-b7c0-1854ed0d934d", "_uuid": "4565479666070f9fd09a98ee414a4095fe2bf1cc"}, "source": ["from sklearn.decomposition import PCA\n", "pca=PCA(n_components=45,svd_solver=\"arpack\")\n", "X_pca=pca.fit_transform(X)\n", "from sklearn.cross_validation import train_test_split\n", "X_train,X_valid,y_train,y_valid=train_test_split(X_pca,y,test_size=0.2)\n", "\n", "print(\"---pca done---\")\n", "print(pca.components_)"], "execution_count": null, "cell_type": "code", "outputs": []}, {"metadata": {"_cell_guid": "584ad00a-76a5-450d-8218-745d7aa92512", "_uuid": "a334e54c20f6848a884be0d2e8aff2af79a89c8c"}, "source": ["print(X_pca)\n", "print(pca.score(X))\n", "print(pca.get_covariance())"], "execution_count": null, "cell_type": "code", "outputs": []}, {"metadata": {"_cell_guid": "70d2370d-fd2b-497b-a4b2-37cfa9fe3db6", "_uuid": "b36822b0eefabfab0d2294e8c218d6bbb55f0eb0"}, "source": ["from sklearn.neighbors import KNeighborsClassifier\n", "print (X_train.shape)"], "execution_count": null, "cell_type": "code", "outputs": []}, {"metadata": {"_cell_guid": "a04ec366-80c6-4ba0-af8f-1694e8665285", "_uuid": "a487017ab9085cd5794ec72e2a321d415f31b1a9"}, "source": ["classifier=KNeighborsClassifier(n_neighbors=4,weights=\"distance\",algorithm=\"kd_tree\",n_jobs=2,leaf_size=10)\n", "print(\"---classifier initalized----\")"], "execution_count": null, "cell_type": "code", "outputs": []}, {"metadata": {"_cell_guid": "744c5b69-5094-4b04-85a8-dcd9108d1dc6", "scrolled": false, "_uuid": "0fa422b3cc92e2dc53647e68030e91c3763e548e"}, "source": ["classifier.fit(X_train,y_train)\n", "pred=classifier.predict(X_valid)\n", "print(\"------Training Done------\")\n"], "execution_count": null, "cell_type": "code", "outputs": []}, {"metadata": {"_cell_guid": "3fc0df50-11c5-4de9-be2c-a1de50dd449d", "_uuid": "496260dcaeb84322e7f9e3145f07e0295084a7a1"}, "source": ["from sklearn.metrics import precision_score\n", "precise_score=precision_score(y_valid,pred,average=\"micro\")\n", "print(precise_score) "], "execution_count": null, "cell_type": "code", "outputs": []}], "nbformat_minor": 1, "nbformat": 4, "metadata": {"language_info": {"version": "3.6.3", "nbconvert_exporter": "python", "mimetype": "text/x-python", "pygments_lexer": "ipython3", "file_extension": ".py", "name": "python", "codemirror_mode": {"version": 3, "name": "ipython"}}, "kernelspec": {"display_name": "Python 3", "name": "python3", "language": "python"}}}