Files
mlessentials/Lab02/Exercise2.01/Exercise2_01.ipynb
T
2021-02-07 15:16:01 +05:00

5.2 KiB

In [ ]:
%matplotlib inline
import matplotlib as mpl
import seaborn as sns
import matplotlib.pyplot as plt
import statsmodels.formula.api as smf
import statsmodels.graphics.api as smg
import pandas as pd
import numpy as np
import patsy
from statsmodels.graphics.correlation import plot_corr
from sklearn.model_selection import train_test_split
plt.style.use('seaborn')
In [ ]:
rawBostonData = pd.read_csv('../Dataset/Boston.csv')
In [ ]:
rawBostonData.head()
In [ ]:
rawBostonData = rawBostonData.dropna()
In [ ]:
rawBostonData = rawBostonData.drop_duplicates()
In [ ]:
list(rawBostonData.columns)
In [ ]:
renamedBostonData = rawBostonData.rename(columns = {'CRIM':'crimeRatePerCapita',
 ' ZN ':'landOver25K_sqft',
 'INDUS ':'non-retailLandProptn',
 'CHAS':'riverDummy',
 'NOX':'nitrixOxide_pp10m',
 'RM':'AvgNo.RoomsPerDwelling',
 'AGE':'ProptnOwnerOccupied',
 'DIS':'weightedDist',
 'RAD':'radialHighwaysAccess',
 'TAX':'propTaxRate_per10K',
 'PTRATIO':'pupilTeacherRatio',
 'LSTAT':'pctLowerStatus',
 'MEDV':'medianValue_Ks'})
renamedBostonData.head()
In [ ]:
renamedBostonData.info()
In [ ]:
renamedBostonData.describe(include=[np.number]).T
In [ ]:
X = renamedBostonData.drop('crimeRatePerCapita', axis = 1)
y = renamedBostonData[['crimeRatePerCapita']]
seed = 10 
test_data_size = 0.3 
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = test_data_size, random_state = seed)
train_data = pd.concat([X_train, y_train], axis = 1)
test_data = pd.concat([X_test, y_test], axis = 1)
In [ ]:
corrMatrix = train_data.corr(method = 'pearson')
xnames=list(train_data.columns)
ynames=list(train_data.columns)
plot_corr(corrMatrix, xnames=xnames, ynames=ynames,\
          title=None, normcolor=False, cmap='RdYlBu_r')