In [28]:

    

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np
import numpy
from scipy.stats import norm
from sklearn.preprocessing import StandardScaler
import scipy
from scipy import  stats
import warnings
warnings.filterwarnings('ignore')
%matplotlib inline


    

In [51]:

    

data =pd.read_csv('dataset/house_predictions_kaggle/train.csv')
data.head()


    

    
Out[51]:







  

    

      

      
Id
      
MSSubClass
      
MSZoning
      
LotFrontage
      
LotArea
      
Street
      
Alley
      
LotShape
      
LandContour
      
Utilities
      
...
      
PoolArea
      
PoolQC
      
Fence
      
MiscFeature
      
MiscVal
      
MoSold
      
YrSold
      
SaleType
      
SaleCondition
      
SalePrice
    
  
  

    

      
0
      
1
      
60
      
RL
      
65.0
      
8450
      
Pave
      
NaN
      
Reg
      
Lvl
      
AllPub
      
...
      
0
      
NaN
      
NaN
      
NaN
      
0
      
2
      
2008
      
WD
      
Normal
      
208500
    
    

      
1
      
2
      
20
      
RL
      
80.0
      
9600
      
Pave
      
NaN
      
Reg
      
Lvl
      
AllPub
      
...
      
0
      
NaN
      
NaN
      
NaN
      
0
      
5
      
2007
      
WD
      
Normal
      
181500
    
    

      
2
      
3
      
60
      
RL
      
68.0
      
11250
      
Pave
      
NaN
      
IR1
      
Lvl
      
AllPub
      
...
      
0
      
NaN
      
NaN
      
NaN
      
0
      
9
      
2008
      
WD
      
Normal
      
223500
    
    

      
3
      
4
      
70
      
RL
      
60.0
      
9550
      
Pave
      
NaN
      
IR1
      
Lvl
      
AllPub
      
...
      
0
      
NaN
      
NaN
      
NaN
      
0
      
2
      
2006
      
WD
      
Abnorml
      
140000
    
    

      
4
      
5
      
60
      
RL
      
84.0
      
14260
      
Pave
      
NaN
      
IR1
      
Lvl
      
AllPub
      
...
      
0
      
NaN
      
NaN
      
NaN
      
0
      
12
      
2008
      
WD
      
Normal
      
250000
    
  

5 rows × 81 columns

In [10]:

    

data.columns


    

    
Out[10]:





Index([u'Id', u'MSSubClass', u'MSZoning', u'LotFrontage', u'LotArea',
       u'Street', u'Alley', u'LotShape', u'LandContour', u'Utilities',
       u'LotConfig', u'LandSlope', u'Neighborhood', u'Condition1',
       u'Condition2', u'BldgType', u'HouseStyle', u'OverallQual',
       u'OverallCond', u'YearBuilt', u'YearRemodAdd', u'RoofStyle',
       u'RoofMatl', u'Exterior1st', u'Exterior2nd', u'MasVnrType',
       u'MasVnrArea', u'ExterQual', u'ExterCond', u'Foundation', u'BsmtQual',
       u'BsmtCond', u'BsmtExposure', u'BsmtFinType1', u'BsmtFinSF1',
       u'BsmtFinType2', u'BsmtFinSF2', u'BsmtUnfSF', u'TotalBsmtSF',
       u'Heating', u'HeatingQC', u'CentralAir', u'Electrical', u'1stFlrSF',
       u'2ndFlrSF', u'LowQualFinSF', u'GrLivArea', u'BsmtFullBath',
       u'BsmtHalfBath', u'FullBath', u'HalfBath', u'BedroomAbvGr',
       u'KitchenAbvGr', u'KitchenQual', u'TotRmsAbvGrd', u'Functional',
       u'Fireplaces', u'FireplaceQu', u'GarageType', u'GarageYrBlt',
       u'GarageFinish', u'GarageCars', u'GarageArea', u'GarageQual',
       u'GarageCond', u'PavedDrive', u'WoodDeckSF', u'OpenPorchSF',
       u'EnclosedPorch', u'3SsnPorch', u'ScreenPorch', u'PoolArea', u'PoolQC',
       u'Fence', u'MiscFeature', u'MiscVal', u'MoSold', u'YrSold', u'SaleType',
       u'SaleCondition', u'SalePrice'],
      dtype='object')

In [12]:

    

data['SalePrice'].describe()


    

    
Out[12]:





count      1460.000000
mean     180921.195890
std       79442.502883
min       34900.000000
25%      129975.000000
50%      163000.000000
75%      214000.000000
max      755000.000000
Name: SalePrice, dtype: float64

In [19]:

    

sns.distplot(data['SalePrice'])
plt.show()


    

In [35]:

    

print("Skewness: ",data['SalePrice'].skew())
print("Skewness: ",data['SalePrice'].kurt())


    

    




('Skewness: ', 1.8828757597682129)
('Skewness: ', 6.5362818600645287)

In [56]:

    

from keras.models import Sequential
from keras.layers import  Dense,Flatten,activations
from sklearn.preprocessing import  StandardScaler
from sklearn.preprocessing import OneHotEncoder
from sklearn.feature_extraction import DictVectorizer as DV


    

In [80]:

    

data_num = data._get_numeric_data()
data_cat = data.select_dtypes(include=["object"]).copy()
print(data.columns.size)
print(data_num.columns.size)
print(data_cat.columns.size)
print(data.shape)
data_cat = data_cat.fillna("zero",axis=1)


    

    




81
38
43
(1460, 81)

In [81]:

    

data_cat[data_cat.isnull().any(axis=1)]
#data_cat = data_cat.drop('Alley',axis=1)
data_cat[data_cat.isnull().any(axis=1)]


    

    
Out[81]:







  

    

      

      
MSZoning
      
Street
      
Alley
      
LotShape
      
LandContour
      
Utilities
      
LotConfig
      
LandSlope
      
Neighborhood
      
Condition1
      
...
      
GarageType
      
GarageFinish
      
GarageQual
      
GarageCond
      
PavedDrive
      
PoolQC
      
Fence
      
MiscFeature
      
SaleType
      
SaleCondition
    
  
  

  

0 rows × 43 columns

In [106]:

    

tot=0
for i in data_cat.columns.tolist():
    j = len(data_cat[i].value_counts())
    tot += j
print(tot)


    

    




268

In [105]:

    

len(data_cat['MSZoning'].value_counts())


    

    
Out[105]:





5

In [58]:

    

#vectoizing the categorical values
vect = DV(sparse=False)
vect_values = vect.fit_transform(data_cat.values)
##one hot encoding the categorical values

enc = OneHotEncoder()
enc.fit(data_cat.values)


    

    




---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-58-01e9bdd7e847> in <module>()
      1 #vectoizing the categorical values
      2 vect = DV(sparse=False)
----> 3 vect_values = vect.fit_transform(data_cat.values)
      4 ##one hot encoding the categorical values
      5 

/home/surya/anaconda2/lib/python2.7/site-packages/sklearn/feature_extraction/dict_vectorizer.pyc in fit_transform(self, X, y)
    229             Feature vectors; always 2-d.
    230         """
--> 231         return self._transform(X, fitting=True)
    232 
    233     def inverse_transform(self, X, dict_type=dict):

/home/surya/anaconda2/lib/python2.7/site-packages/sklearn/feature_extraction/dict_vectorizer.pyc in _transform(self, X, fitting)
    165         # same time
    166         for x in X:
--> 167             for f, v in six.iteritems(x):
    168                 if isinstance(v, six.string_types):
    169                     f = "%s%s%s" % (f, self.separator, v)

/home/surya/anaconda2/lib/python2.7/site-packages/sklearn/externals/six.pyc in iteritems(d, **kw)
    437 def iteritems(d, **kw):
    438     """Return an iterator over the (key, value) pairs of a dictionary."""
--> 439     return iter(getattr(d, _iteritems)(**kw))
    440 
    441 def iterlists(d, **kw):

AttributeError: 'numpy.ndarray' object has no attribute 'iteritems'

In [37]:

    

model = Sequential()
model.add(Dense(79))