
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import warnings
import seaborn as sns
warnings.filterwarnings('ignore')


df = pd.read_csv('House_Rent_Dataset.csv')


df.head()


df.sample()


df.shape

(4746, 12)


df.columns

Index(['Posted On', 'BHK', 'Rent', 'Size', 'Floor', 'Area Type',
       'Area Locality', 'City', 'Furnishing Status', 'Tenant Preferred',
       'Bathroom', 'Point of Contact'],
      dtype='object')


df.hist(bins=30 ,figsize=(20,15))
plt.show()


plt.figure()
sns.heatmap(df.corr() , annot=True , cmap="PuBu")

<AxesSubplot:>


sns.countplot(df['Area Type'])

<AxesSubplot:xlabel='Area Type', ylabel='count'>


sns.countplot(df['Furnishing Status'])

<AxesSubplot:xlabel='Furnishing Status', ylabel='count'>


sns.countplot(df['Tenant Preferred'])

<AxesSubplot:xlabel='Tenant Preferred', ylabel='count'>


sns.countplot(df['City'])

<AxesSubplot:xlabel='City', ylabel='count'>


sns.set_context('notebook', font_scale = 1.3)
plt.figure(figsize=(22, 7))
ax = sns.barplot(x=df['City'], 
                 y=df['Rent'],
                 hue = df['Furnishing Status'], 
                 palette='viridis',
                 ci = None)
plt.ylabel('Rent');

for p in ax.patches:
    ax.annotate(int(p.get_height()), (p.get_x() + 0.14, p.get_height() + 1), ha = 'center', va = 'bottom', color = 'Black')


df['Posted On'] = pd.to_datetime(df['Posted On'])
df['month posted'] = df['Posted On'].dt.month


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 4746 entries, 0 to 4745
Data columns (total 13 columns):
 #   Column             Non-Null Count  Dtype         
---  ------             --------------  -----         
 0   Posted On          4746 non-null   datetime64[ns]
 1   BHK                4746 non-null   int64         
 2   Rent               4746 non-null   int64         
 3   Size               4746 non-null   int64         
 4   Floor              4746 non-null   object        
 5   Area Type          4746 non-null   object        
 6   Area Locality      4746 non-null   object        
 7   City               4746 non-null   object        
 8   Furnishing Status  4746 non-null   object        
 9   Tenant Preferred   4746 non-null   object        
 10  Bathroom           4746 non-null   int64         
 11  Point of Contact   4746 non-null   object        
 12  month posted       4746 non-null   int64         
dtypes: datetime64[ns](1), int64(5), object(7)
memory usage: 482.1+ KB


df.drop('Posted On', axis = 1, inplace= True)

df


df['Floor']=df['Floor'].str[0]


df['Floor']=df['Floor'].map({'L':-1,'G':0,"U":0,'1':1,'2':2,'3':3,'4':4,'5':5,'6':6,'7':7,'8':8,'9':9})


df["Floor"].unique()

array([ 0,  1,  2,  4,  3,  5,  7,  8, -1,  6,  9], dtype=int64)


df['Area Type'].unique()

array(['Super Area', 'Carpet Area', 'Built Area'], dtype=object)


def one_hot_encode(data, column):
    encoded = pd.get_dummies(data[column], drop_first= True)
    data = data.drop(column, axis = 1)
    data = data.join(encoded)
    return data


features = ['Area Type','City', 'Furnishing Status', 'Tenant Preferred', 'Point of Contact']

for feature in features:
   df =  one_hot_encode(df, feature)


df.sample(5)


df.drop('Area Locality',axis=1,inplace=True)


from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split, cross_val_score, KFold
from scipy.stats import probplot, boxcox
from scipy.special import inv_boxcox
from sklearn.linear_model import LinearRegression, Ridge
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import RandomForestRegressor, GradientBoostingRegressor


x = df.drop("Rent", axis = 1)


df['Rent'] = np.log(df['Rent'])


y = df.iloc[:,1]


x_train, x_test, y_train, y_test= train_test_split(x, y, test_size=0.20,random_state=40)


sc = StandardScaler()
x_train = sc.fit_transform(x_train)
x_test = sc.transform(x_test)


lr = LinearRegression()
scores = cross_val_score(lr, x_test, y_test, scoring='r2', cv=5)
print(scores)
print(np.mean(scores))

[0.81063636 0.82698973 0.78587266 0.78989185 0.75429624]
0.7935373679222344


from sklearn.preprocessing import PolynomialFeatures


poly = PolynomialFeatures(2)
data_poly = poly.fit_transform(x_train)


lr = Ridge(alpha=5000)
np.mean(cross_val_score(lr, data_poly[:, 1:], y_train, scoring='r2', cv=5)).round(2)

0.74


rf = RandomForestRegressor(n_estimators=100, max_depth=10)
np.mean(cross_val_score(rf, data_poly[:, 1:], y_train, scoring='r2', cv=5)).round(2)

0.82


rf = RandomForestRegressor(n_estimators=100, max_depth=10)
rf.fit(data_poly[:, 1:], y_train)
y_pred = rf.predict(poly.transform(x_test)[:, 1:])


from sklearn.metrics import r2_score


score = r2_score(y_test, y_pred)


score

0.8067773953617802

	Posted On	BHK	Rent	Size	Floor	Area Type	Area Locality	City	Furnishing Status	Tenant Preferred	Bathroom	Point of Contact
0	2022-05-18	2	10000	1100	Ground out of 2	Super Area	Bandel	Kolkata	Unfurnished	Bachelors/Family	2	Contact Owner
1	2022-05-13	2	20000	800	1 out of 3	Super Area	Phool Bagan, Kankurgachi	Kolkata	Semi-Furnished	Bachelors/Family	1	Contact Owner
2	2022-05-16	2	17000	1000	1 out of 3	Super Area	Salt Lake City Sector 2	Kolkata	Semi-Furnished	Bachelors/Family	1	Contact Owner
3	2022-07-04	2	10000	800	1 out of 2	Super Area	Dumdum Park	Kolkata	Unfurnished	Bachelors/Family	1	Contact Owner
4	2022-05-09	2	7500	850	1 out of 2	Carpet Area	South Dum Dum	Kolkata	Unfurnished	Bachelors	1	Contact Owner

	BHK	Rent	Size	Floor	Area Type	Area Locality	City	Furnishing Status	Tenant Preferred	Bathroom	Point of Contact	month posted
0	2	10000	1100	Ground out of 2	Super Area	Bandel	Kolkata	Unfurnished	Bachelors/Family	2	Contact Owner	5
1	2	20000	800	1 out of 3	Super Area	Phool Bagan, Kankurgachi	Kolkata	Semi-Furnished	Bachelors/Family	1	Contact Owner	5
2	2	17000	1000	1 out of 3	Super Area	Salt Lake City Sector 2	Kolkata	Semi-Furnished	Bachelors/Family	1	Contact Owner	5
3	2	10000	800	1 out of 2	Super Area	Dumdum Park	Kolkata	Unfurnished	Bachelors/Family	1	Contact Owner	7
4	2	7500	850	1 out of 2	Carpet Area	South Dum Dum	Kolkata	Unfurnished	Bachelors	1	Contact Owner	5
...	...	...	...	...	...	...	...	...	...	...	...	...
4741	2	15000	1000	3 out of 5	Carpet Area	Bandam Kommu	Hyderabad	Semi-Furnished	Bachelors/Family	2	Contact Owner	5
4742	3	29000	2000	1 out of 4	Super Area	Manikonda, Hyderabad	Hyderabad	Semi-Furnished	Bachelors/Family	3	Contact Owner	5
4743	3	35000	1750	3 out of 5	Carpet Area	Himayath Nagar, NH 7	Hyderabad	Semi-Furnished	Bachelors/Family	3	Contact Agent	7
4744	3	45000	1500	23 out of 34	Carpet Area	Gachibowli	Hyderabad	Semi-Furnished	Family	2	Contact Agent	7
4745	2	15000	1000	4 out of 5	Carpet Area	Suchitra Circle	Hyderabad	Unfurnished	Bachelors	2	Contact Owner	5

	BHK	Rent	Size	Floor	Area Locality	Bathroom	month posted	Carpet Area	Super Area	Chennai	Delhi	Semi-Furnished	Unfurnished	Bachelors/Family	Family	Contact Owner
1643	2	8000	600	1	Electronic City	1	6	0	1	0	0	0	1	1	0	1
2931	3	90000	1550	2	Safdarjung Enclave	3	7	1	0	0	1	1	0	0	0	0
3661	1	7000	400	0	Nanmangalam	1	6	0	1	1	0	1	0	1	0	1
3440	2	18000	1100	0	Purasawalkam, PH Road	2	6	0	1	1	0	1	0	1	0	1
3804	3	37000	1650	2	Vadapalani	3	5	0	1	1	0	1	0	0	1	0

Importing Libraries for EDA¶

Using Machine Learning Libraries¶