import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np
from scipy.stats import norm
from sklearn.preprocessing import StandardScaler
from scipy import stats
import warnings
warnings.filterwarnings('ignore')
%matplotlib inlinetrain = pd.read_csv('input/train.csv')
test = pd.read_csv('input/test.csv')

sample = pd.read_csv('input/sample_submission.csv')corrmat = train.corr()
f, ax = plt.subplots(figsize=(12, 9))
sns.heatmap(corrmat, vmax=.8, square=True)

k = 10
cols = corrmat.nlargest(k, 'SalePrice')['SalePrice'].index
cm = np.corrcoef(train[cols].values.T)
sns.set(font_scale=1.25)
hm = sns.heatmap(cm, cbar=True, annot=True, square=True, fmt='.2f', annot_kws={'size': 10}, yticklabels=cols.values, xticklabels=cols.values)
plt.show()

sns.set()
cols = ['SalePrice', 'OverallQual', 'GrLivArea', 'GarageCars', 'TotalBsmtSF', 'FullBath', 'YearBuilt']
sns.pairplot(train[cols], size = 2.5)
plt.show()

train_Id = train['Id']
test_Id = test['Id']
len_train = train.shape[0]
len_test = test.shape[0]
housing = pd.concat([train, test], sort=False)
housing.shape
(2919, 81)
housing[cols].columns
Index(['SalePrice', 'OverallQual', 'GrLivArea', 'GarageCars', 'TotalBsmtSF','FullBath', 'YearBuilt'],dtype='object')
housing = housing[cols]

housing.isnull().sum()
SalePrice      1459
OverallQual       0
GrLivArea         0
GarageCars        1
TotalBsmtSF       1
FullBath          0
YearBuilt         0
dtype: int64
housing.GarageCars = housing.GarageCars.fillna(housing.GarageCars.mean())
housing.TotalBsmtSF = housing.TotalBsmtSF.fillna(housing.TotalBsmtSF.mean())
train = housing[:len_train]
test = housing[len_train:]

xtrain=train.drop("SalePrice",axis=1)
ytrain=train['SalePrice']
xtest=test.drop("SalePrice", axis=1)
from math import sqrt
train_X, val_X, train_y, val_y = train_test_split(xtrain, ytrain, random_state=1)
my_pipeline = XGBRegressor(n_estimators=1000, learning_rate=0.05)
my_pipeline.fit(train_X, train_y)
val_preds = my_pipeline.predict(val_X)
msel = mean_squared_error(np.log(val_preds), np.log(val_y))
print("RMSE: %2f" %sqrt(msel))
RMSE: 0.173459
test_preds = my_pipeline.predict(xtest)output = pd.DataFrame({'Id': test_Id,'SalePrice': test_preds})
output.set_index('Id').to_csv('submission.csv')

var = 'GrLivArea'
data = pd.concat([train['SalePrice'], train[var]], axis=1)
data.plot.scatter(x=var, y='SalePrice', ylim=(0,800000));
'c' argument looks like a single numeric RGB or RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches with 'x' & 'y'.  Please use a 2-D array with a single row if you really want to specify the same RGB or RGBA value for all points.

train = train.drop(train[train.index == 1298].index)
train = train.drop(train[train.index == 523].index)
var = 'GrLivArea'
data = pd.concat([train['SalePrice'], train[var]], axis=1)
data.plot.scatter(x=var, y='SalePrice', ylim=(0,800000));
'c' argument looks like a single numeric RGB or RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches with 'x' & 'y'.  Please use a 2-D array with a single row if you really want to specify the same RGB or RGBA value for all points.

xtrain=train.drop("SalePrice",axis=1)
ytrain=train['SalePrice']
xtest=test.drop("SalePrice", axis=1)
from math import sqrt
train_X, val_X, train_y, val_y = train_test_split(xtrain, ytrain, random_state=1)my_pipeline = XGBRegressor(n_estimators=1000, learning_rate=0.05)
my_pipeline.fit(train_X, train_y)val_preds = my_pipeline.predict(val_X)
msel = mean_squared_error(np.log(val_preds), np.log(val_y))
print("RMSE: %2f" %sqrt(msel))
RMSE: 0.162534
test_preds = my_pipeline.predict(xtest)output = pd.DataFrame({'Id': test_Id,'SalePrice': test_preds})
output.set_index('Id').to_csv('submission2.csv')