
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

import seaborn as sns
from scipy.stats import skew, norm

import scipy.stats as stats
import warnings
warnings.filterwarnings('ignore')


from google.colab import files
upload_train = files.upload()

Saving house-train.csv to house-train.csv


import pandas as pd
import io
train = pd.read_csv(io.BytesIO(upload_train['house-train.csv']), index_col=None)
train.shape

(1460, 81)


quantitative = [f for f in train.columns if train.dtypes[f] != 'object']
quantitative.remove('SalePrice')
quantitative.remove('Id')
qualitative = [f for f in train.columns if train.dtypes[f] == 'object']


for c in qualitative:
    train[c] = train[c].astype('category')
    if train[c].isnull().any():
        train[c] = train[c].cat.add_categories(['MISSING'])
        train[c] = train[c].fillna('MISSING')


def anova(frame):
    anv = pd.DataFrame()
    anv['feature'] = qualitative
    pvals = []
    for c in qualitative:
        samples = []
        for cls in frame[c].unique():
            s = frame[frame[c] == cls]['SalePrice'].values
            samples.append(s)
        pval = stats.f_oneway(*samples)[1]
        pvals.append(pval)
    anv['pval'] = pvals
    return anv.sort_values('pval')

a = anova(train)
a['disparity'] = np.log(1./a['pval'].values)
print(a)

          feature           pval   disparity
8    Neighborhood  1.558600e-225  517.637858
18      ExterQual  1.439551e-204  469.363028
21       BsmtQual  8.158548e-196  449.207612
30    KitchenQual  3.032213e-192  440.987045
34   GarageFinish  6.228747e-115  262.968110
32    FireplaceQu  2.971217e-107  245.287633
20     Foundation   5.791895e-91  207.778784
33     GarageType   6.117026e-87  198.513827
24   BsmtFinType1   2.386358e-71  162.613773
27      HeatingQC   2.667062e-67  153.292224
17     MasVnrType   1.054025e-64  147.312830
23   BsmtExposure   7.557758e-50  113.106680
42  SaleCondition   7.988268e-44   99.235770
15    Exterior1st   2.586089e-43   98.061012
16    Exterior2nd   4.842186e-43   97.433793
41       SaleType   5.039767e-42   95.091214
0        MSZoning   8.817634e-35   78.413725
12     HouseStyle   3.376777e-25   56.347706
35     GarageQual   5.388762e-25   55.880312
36     GarageCond   5.711746e-25   55.822103
3        LotShape   6.447524e-25   55.700931
28     CentralAir   1.809506e-22   50.063818
37     PavedDrive   1.803569e-18   40.856764
29     Electrical   8.226925e-18   39.339119
13      RoofStyle   3.653523e-17   37.848255
22       BsmtCond   8.195794e-16   34.737740
39          Fence   9.379977e-11   23.089859
11       BldgType   2.056736e-10   22.304730
4     LandContour   2.742217e-08   17.411914
25   BsmtFinType2   5.225649e-08   16.767102
14       RoofMatl   7.231445e-08   16.442242
9      Condition1   8.904549e-08   16.234118
2           Alley   2.996380e-07   15.020691
19      ExterCond   5.106681e-07   14.487546
38         PoolQC   7.700989e-07   14.076747
6       LotConfig   3.163167e-06   12.663937
31     Functional   4.841697e-04    7.633075
26        Heating   7.534721e-04    7.190819
40    MiscFeature   3.500367e-02    3.352302
10     Condition2   4.342566e-02    3.136705
1          Street   1.170486e-01    2.145166
7       LandSlope   1.413964e-01    1.956188
5       Utilities   5.847168e-01    0.536628


plt.figure(figsize = (25, 8)) 
sns.barplot(data=a, x='feature', y='disparity')
x=plt.xticks(rotation=90)