# -*- coding: utf-8 -*-

"""Advanced_House_Prediction.ipynb

Automatically generated by Colaboratory.

Original file is located at

https://colab.research.google.com/drive/1sUbRhTeJwKKAqn2hm5lxGALSna2mfjsM

"""

import zipfile

with zipfile.ZipFile('./house-prices-advanced-regression-techniques.zip', 'r') as zip_ref:

zip_ref.extractall('./')

import pandas as pd

import numpy as np

train_data=pd.read_csv('./train.csv')

test_data=pd.read_csv('./test.csv')

train_data.head(10)

test_data.head()

train_data.info()

test_data.info()

## Top 20 Fields of train data having null values

train_data.isnull().sum().sort_values(ascending=False).iloc[:20]

## Top 35 Fields of test data having null values

test_data.isnull().sum().sort_values(ascending=False).iloc[:35]

len(train_data),len(test_data)

train_data.columns

test_data['Alley'].isnull().sum()

def filter(dataset):

return dataset

train_data = filter(train_data)

test_data = filter(test_data)

train_data.isnull().sum().sort_values(ascending=False).iloc[:20]

## Top 35 Fields of test data having null values

test_data.isnull().sum().sort_values(ascending=False).iloc[:35]

train_data.info()

test_data.info()

from sklearn.neighbors import KNeighborsClassifier

knn = KNeighborsClassifier(n_neighbors=7)

knn.fit(X_train, y_train)

# Predict on dataset which model has not seen before

print(knn.predict(X_test))

def filter1(dataset):

return dataset

train_data=filter1(train_data)

test_data=filter1(test_data)

## Top 5 Fields of test data having null values

test_data.isnull().sum().sort_values(ascending=False).iloc[:5]

## Top 5 Fields of test data having null values

train_data.isnull().sum().sort_values(ascending=False).iloc[:5]

import seaborn as sns

import matplotlib.pyplot as plt

from scipy.stats import norm

interested_col=[]

for item in train_data.corr().reset_index()[['index','SalePrice']].values:

if item[1:2]>=0.7 or item[1:2]<=-0.7:

interested_col.append(item[0:1][0])

interested_col.remove('SalePrice')

print(interested_col)

tt = train_data.columns.append(test_data.columns)

tt=list(dict.fromkeys(tt))

for i in tt:

if i not in test_data.columns:

print(i)

train_data_len = len(train_data)

test_data_len = len(test_data)

print(train_data_len,test_data_len)

print(train_data.shape,test_data.shape)

total = pd.concat([train_data.drop(['SalePrice'],axis=1),test_data],axis=0) # .drop(['SalePrice'],axis=1)

total.shape

column=['MSZoning','Street','LotShape','LandContour','Utilities','LotConfig','LandSlope','Neighborhood',

'GarageType','GarageFinish','GarageQual','GarageCond','PavedDrive']

columns=column+interested_col

print(columns)

total = total[columns]

total.shape

def category_onehot_multcols(multcolumns):

return df_final

total=category_onehot_multcols(column)

total.shape

total = total.loc[:,~total.columns.duplicated()]

total.shape

save_cols=total.columns

from sklearn.preprocessing import StandardScaler

x = total.values

x = StandardScaler().fit_transform(x)

x.shape

x=pd.DataFrame(x,columns=save_cols)

from sklearn.decomposition import PCA

pca = PCA(n_components=20)

principalComponents = pca.fit_transform(x)

Df = pd.DataFrame(data = principalComponents, columns = ['pc1', 'pc2','pc3','pc4','pc5','pc6','pc7','pc8','pc9','pc10','pc11', 'pc12','pc13','pc14','pc15','pc16','pc17','pc18','pc19','pc20'])

print('Explained variation per principal component: {}'.format(pca.explained_variance_ratio_))

# Df.shape # (2919, 20)

train = x.iloc[:1460]

test = x.iloc[1460:]

print(train.shape,test.shape)

X_train=train

y_train=train_data['SalePrice']

X_test=test

X_train.shape,y_train.shape,X_test.shape

from tensorflow.keras import backend as K

def root_mean_squared_error(y_true, y_pred):

return K.sqrt(K.mean(K.square(y_pred - y_true)))

from sklearn.ensemble import RandomForestRegressor

# create regressor object

regressor = RandomForestRegressor(n_estimators = 500, random_state = 0)

# fit the regressor with x and y data

regressor.fit(X_train, y_train)

y_pred = regressor.predict(X_test)

from sklearn.ensemble import GradientBoostingRegressor

from sklearn.metrics import mean_squared_error

from sklearn.metrics import mean_absolute_error

regressor = GradientBoostingRegressor(

)

regressor.fit(X_train, y_train)

errors = [root_mean_squared_error(y_train, y_pred) for y_pred in regressor.staged_predict(X_train)]

best_n_estimators = np.argmin(errors)

best_regressor = GradientBoostingRegressor(

)

best_regressor.fit(X_train, y_train)

y_pred = best_regressor.predict(X_test)

import tensorflow as tf

from tensorflow import keras

from tensorflow.keras.models import Sequential

from tensorflow.keras.layers import Dense

from tensorflow.keras.layers import LeakyReLU,PReLU,ELU

from tensorflow.keras.layers import Dropout

# Initialising the ANN

classifier = Sequential()

# Adding the input layer and the first hidden layer

classifier.add(Dense(50, kernel_initializer = 'he_uniform', activation='relu',input_dim = 146))

# Adding the second hidden layer

classifier.add(Dense(25, kernel_initializer = 'he_uniform', activation='relu'))

# Adding the third hidden layer

classifier.add(Dense(50, kernel_initializer = 'he_uniform', activation='relu'))

# Adding the output layer

classifier.add(Dense(1, kernel_initializer = 'he_uniform', use_bias=True))

# Compiling the ANN

classifier.compile(loss=root_mean_squared_error, optimizer='Adamax')

# Fitting the ANN to the Training set

model_history=classifier.fit(X_train.values, y_train.values,validation_split=0.20, batch_size = 10, epochs = 760)

import xgboost as xgb

data_dmatrix = xgb.DMatrix(data=X_train,label=y_train)

xg_reg = xgb.XGBRegressor(objective ='reg:linear', colsample_bytree = 0.3, learning_rate = 0.1,max_depth = 5, alpha = 10, n_estimators = 500)

xg_reg.fit(X_train,y_train)

y_pred = xg_reg.predict(X_test)

params = {"objective":"reg:linear",'colsample_bytree': 0.3,'learning_rate': 0.1,

'max_depth': 5, 'alpha': 10}

cv_results = xgb.cv(dtrain=data_dmatrix, params=params, nfold=3,

num_boost_round=50,early_stopping_rounds=10,metrics="rmse", as_pandas=True, seed=123)

cv_results.head()

y_pred=classifier.predict(test)

pred=pd.DataFrame(y_pred)

sub_df=pd.read_csv('sample_submission.csv')

datasets=pd.concat([sub_df['Id'],pred],axis=1)

datasets.columns=['Id','SalePrice']

datasets.to_csv('sample_submission.csv',index=False)

datasets.head()