{ "cells": [ { "cell_type": "markdown", "metadata": { "_cell_guid": "8e8da892-22e7-9c47-1ddc-281fbef3236a" }, "source": "" }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "d52b4c81-a8cb-9282-76b2-18e2bc8a3344" }, "outputs": [], "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", "from sklearn.decomposition import PCA\n", "from sklearn.preprocessing import Imputer\n", "from sklearn.model_selection import KFold\n", "from sklearn import linear_model\n", "from sklearn.metrics import make_scorer\n", "from sklearn.ensemble import BaggingRegressor\n", "from sklearn.ensemble import RandomForestRegressor\n", "from sklearn import svm\n", "from sklearn.metrics import r2_score\n", "from sklearn.ensemble import AdaBoostRegressor\n", "from sklearn.model_selection import cross_val_score\n", "from sklearn.tree import DecisionTreeRegressor\n", "from sklearn.model_selection import GridSearchCV\n", "import matplotlib.pyplot as plt\n", "import tflearn\n", "import tensorflow as tf\n", "import seaborn\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." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "fdfc434d-3a10-58da-9efd-54fec9c9a679" }, "outputs": [], "source": [ "train = pd.read_csv('../input/train.csv')\n", "#train.head()\n", "test = pd.read_csv('../input/test.csv')\n", "y = train.SalePrice\n", "data = pd.concat([train,test],ignore_index=True)\n", "data = data.drop(\"SalePrice\",1)\n", "print (data.shape)\n", "#print (train.shape)\n", "#print (test.shape)\n", "#train.head()\n", "#y = train.iloc[:,-1][:,np.newaxis]\n", "#y.head()\n", "#X = train.iloc[:,:-1]\n", "#print (X)\n", "#y.head()\n", "#print (X.shape)\n", "#print (y.shape)\n", "#X.isnull().sum()\n", "nans = pd.isnull(data).sum()\n", "nans = nans[nans>0]\n", "print (nans)\n", "#print (nans.columns)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "1b689475-213f-9285-e119-30c74774964e" }, "outputs": [], "source": [ "'''from sklearn.decomposition import PCA\n", "from sklearn.model_selection import train_test_split\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)\n", "X_train_reduced = PCA(n_components=2).fit_transform(X_train)\n", "fig = plt.figure(1,figsize=(8,6))\n", "ax = Axes3D(fig, elev=-150, azim=110)\n", "ax.scatter(X_train_reduced[:,0],X_train_reduced[:,1],y_train[:],c='r',cmap=plt.cm.Paired)\n", "ax.set_title(\"First two PCA directions\")\n", "ax.set_xlabel(\"1st eigenvector\")\n", "ax.w_xaxis.set_ticklabels([])\n", "ax.set_ylabel(\"2nd eigenvector\")\n", "ax.w_yaxis.set_ticklabels([])\n", "ax.set_zlabel(\"the price\")\n", "ax.w_zaxis.set_ticklabels([])\n", "plt.show()\n", "'''" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "1685c07b-d242-edef-55ff-ff2fd8896ad3" }, "outputs": [], "source": [ "data = data.drop('Id',1)\n", "data = data.drop('Alley',1)\n", "data = data.drop('Fence',1)\n", "data = data.drop('FireplaceQu',1)\n", "data = data.drop('MiscFeature',1)\n", "data = data.drop('PoolQC',1)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "c00730b3-0345-07b8-00ec-ce0d6a6bf3db" }, "outputs": [], "source": [ "data.shape" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "b90a2c8f-01dc-f5d1-3efe-83b35588ddae" }, "outputs": [], "source": [ "data.dtypes.value_counts()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "28f47330-17fa-a787-3f84-dddce72c22c7" }, "outputs": [], "source": [ "all_columns = data.columns.values\n", "non_categorical = [\"LotFrontage\", \"LotArea\", \"MasVnrArea\", \"BsmtFinSF1\", \n", " \"BsmtFinSF2\", \"BsmtUnfSF\", \"TotalBsmtSF\", \"1stFlrSF\", \n", " \"2ndFlrSF\", \"LowQualFinSF\", \"GrLivArea\", \"GarageArea\", \n", " \"WoodDeckSF\", \"OpenPorchSF\", \"EnclosedPorch\", \"3SsnPorch\", \n", " \"ScreenPorch\",\"PoolArea\", \"MiscVal\"]\n", "categorical = [x for x in all_columns if x not in non_categorical]" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "1ad725e8-8f5d-ee3d-316e-ebb902450ce4" }, "outputs": [], "source": [ "data = pd.get_dummies(data)\n", "imp = Imputer(missing_values='NaN',strategy='most_frequent',axis=0)\n", "data = imp.fit_transform(data)\n", "# log transformation I do not understand\n", "data = np.log(data)\n", "labels = np.log(y)\n", "data[data==-np.inf] = 0" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "3e874400-c660-9ff0-dbe8-4e4f72cf424c" }, "outputs": [], "source": [ "pca = PCA(whiten=True)\n", "pca.fit(data)\n", "variance = pd.DataFrame(pca.explained_variance_ratio_)\n", "print (np.cumsum(pca.explained_variance_ratio_))" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "0a54acb8-7d0c-b744-afa3-073b6fbdb775" }, "outputs": [], "source": [ "pca = PCA(n_components=36,whiten=True)\n", "pca = pca.fit(data)\n", "pca_data = pca.transform(data)\n", "pca_data.shape" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "b033b21a-651b-387a-a1aa-44741a2340af" }, "outputs": [], "source": [ "pca_train = pca_data[:1460,:]\n", "pca_test = pca_data[1460:,:]" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "150a65a8-2617-6d3c-5a4b-273820c65aa1" }, "outputs": [], "source": [ "def lets_try(train,labels):\n", " results={}\n", " def test_model(clf):\n", " \n", " cv = KFold(n_splits=5,shuffle=True,random_state=45)\n", " r2 = make_scorer(r2_score)\n", " r2_val_score = cross_val_score(clf, train, labels, cv=cv,scoring=r2)\n", " scores=[r2_val_score.mean()]\n", " return scores\n", "\n", " clf = linear_model.LinearRegression()\n", " results[\"Linear\"]=test_model(clf)\n", " \n", " clf = linear_model.Ridge()\n", " results[\"Ridge\"]=test_model(clf)\n", " \n", " clf = linear_model.BayesianRidge()\n", " results[\"Bayesian Ridge\"]=test_model(clf)\n", " \n", " clf = linear_model.HuberRegressor()\n", " results[\"Hubber\"]=test_model(clf)\n", " \n", " clf = linear_model.Lasso(alpha=1e-4)\n", " results[\"Lasso\"]=test_model(clf)\n", " \n", " clf = BaggingRegressor()\n", " results[\"Bagging\"]=test_model(clf)\n", " \n", " clf = RandomForestRegressor()\n", " results[\"RandomForest\"]=test_model(clf)\n", " \n", " clf = AdaBoostRegressor()\n", " results[\"AdaBoost\"]=test_model(clf)\n", " \n", " clf = svm.SVR()\n", " results[\"SVM RBF\"]=test_model(clf)\n", " \n", " clf = svm.SVR(kernel=\"linear\")\n", " results[\"SVM Linear\"]=test_model(clf)\n", " \n", " results = pd.DataFrame.from_dict(results,orient='index')\n", " results.columns=[\"R Square Score\"] \n", " results=results.sort(columns=[\"R Square Score\"],ascending=False)\n", " results.plot(kind=\"bar\",title=\"Model Scores\")\n", " axes = plt.gca()\n", " axes.set_ylim([0.5,1])\n", " return results\n", "\n", "lets_try(pca_train,labels)" ] } ], "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": "3.6.0" } }, "nbformat": 4, "nbformat_minor": 0 }