Feature Importance Practice¶

Practice at assessing the feature importance of a dataset based on the highest gini gain¶

A dataset with apartment features and montly rent was used.¶

In [1]:
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
import matplotlib.pyplot as plt

Import Libraries, File and Inspect Head¶

In [2]:
df = pd.read_csv('ManhattanHousing.csv')
In [3]:
df.head()
Out[3]:
rental_id rent bedrooms bathrooms size_sqft min_to_subway floor building_age_yrs no_fee has_roofdeck has_washer_dryer has_doorman has_elevator has_dishwasher has_patio has_gym neighborhood borough
0 1545 2550 0.0 1 480 9 2.0 17 1 1 0 0 1 1 0 1 Upper East Side Manhattan
1 2472 11500 2.0 2 2000 4 1.0 96 0 0 0 0 0 0 0 0 Greenwich Village Manhattan
2 2919 4500 1.0 1 916 2 51.0 29 0 1 0 1 1 1 0 0 Midtown Manhattan
3 2790 4795 1.0 1 975 3 8.0 31 0 0 0 1 1 1 0 1 Greenwich Village Manhattan
4 3946 17500 2.0 2 4800 3 4.0 136 0 0 0 1 1 1 0 1 Soho Manhattan

Split the Data¶

In [4]:
x = df[['bedrooms', 'bathrooms', 'size_sqft', 'min_to_subway', 'floor', 'building_age_yrs', 'no_fee', 'has_roofdeck', 'has_washer_dryer', 'has_doorman', 'has_elevator', 'has_dishwasher', 'has_patio', 'has_gym']]

y = df[['rent']]

x_train, x_test, y_train, y_test = train_test_split(x, y, train_size=0.8, test_size=0.2)

Fit A Decision Tree to the Model¶

In [5]:
clf = DecisionTreeClassifier(criterion='gini')

clf = clf.fit(x_train, y_train)

Create a Dictionary of Features and their Importance¶

In [6]:
feature_importances = clf.feature_importances_
In [7]:
column_names = x_train.columns

feature_importance_dict = dict(zip(column_names, feature_importances))

Assess Feature Importance¶

In [8]:
sorted_feature_importance = sorted(feature_importance_dict.items(), key=lambda x: x[1], reverse=True)

print(sorted_feature_importance)

[('size_sqft', 0.19370695155593112), ('floor', 0.19106434380874543), ('building_age_yrs', 0.18732609467033248), ('min_to_subway', 0.15155380021152945), ('bedrooms', 0.06072393803989258), ('has_doorman', 0.03185215681807589), ('has_elevator', 0.030288746802205425), ('no_fee', 0.026845148178826852), ('has_washer_dryer', 0.026581151325924222), ('has_dishwasher', 0.023933827353835042), ('has_gym', 0.020814343880004305), ('has_roofdeck', 0.020672676860949684), ('bathrooms', 0.020298547272458292), ('has_patio', 0.014338273221289421)]

Visualise Feature Importance¶

In [9]:
features = [item[0] for item in sorted_feature_importance]
importances = [item[1] for item in sorted_feature_importance]

plt.figure(figsize=(10, 6))
plt.barh(range(len(features)), importances, align='center')
plt.yticks(range(len(features)), features)
plt.xlabel('Importance')
plt.ylabel('Feature')
plt.title('Feature Importances')
plt.gca().invert_yaxis()
plt.show()
In [ ]: