Investigating customer data to determine how to best encourage customers to spend more for the duration of their customer lifecycle.
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn import metrics
sns.set()
%matplotlib inline
# Load data and confirm it was loaded
customers = pd.read_csv('Fake Ecommerce Customers.csv')
customers.head()
<style scoped>
.dataframe tbody tr th:only-of-type {
vertical-align: middle;
}
.dataframe tbody tr th {
vertical-align: top;
}
.dataframe thead th {
text-align: right;
}
</style>
|
Email |
Address |
Avatar |
Avg. Session Length |
Time on App |
Time on Website |
Length of Membership |
Yearly Amount Spent |
0 |
mstephenson@fernandez.com |
835 Frank Tunnel\nWrightmouth, MI 82180-9605 |
Violet |
34.497268 |
12.655651 |
39.577668 |
4.082621 |
587.951054 |
1 |
hduke@hotmail.com |
4547 Archer Common\nDiazchester, CA 06566-8576 |
DarkGreen |
31.926272 |
11.109461 |
37.268959 |
2.664034 |
392.204933 |
2 |
pallen@yahoo.com |
24645 Valerie Unions Suite 582\nCobbborough, D... |
Bisque |
33.000915 |
11.330278 |
37.110597 |
4.104543 |
487.547505 |
3 |
riverarebecca@gmail.com |
1414 David Throughway\nPort Jason, OH 22070-1220 |
SaddleBrown |
34.305557 |
13.717514 |
36.721283 |
3.120179 |
581.852344 |
4 |
mstephens@davidson-herman.com |
14023 Rodriguez Passage\nPort Jacobville, PR 3... |
MediumAquaMarine |
33.330673 |
12.795189 |
37.536653 |
4.446308 |
599.406092 |
# Take a look at our data's characteristics
customers.describe()
<style scoped>
.dataframe tbody tr th:only-of-type {
vertical-align: middle;
}
.dataframe tbody tr th {
vertical-align: top;
}
.dataframe thead th {
text-align: right;
}
</style>
|
Avg. Session Length |
Time on App |
Time on Website |
Length of Membership |
Yearly Amount Spent |
count |
500.000000 |
500.000000 |
500.000000 |
500.000000 |
500.000000 |
mean |
33.053194 |
12.052488 |
37.060445 |
3.533462 |
499.314038 |
std |
0.992563 |
0.994216 |
1.010489 |
0.999278 |
79.314782 |
min |
29.532429 |
8.508152 |
33.913847 |
0.269901 |
256.670582 |
25% |
32.341822 |
11.388153 |
36.349257 |
2.930450 |
445.038277 |
50% |
33.082008 |
11.983231 |
37.069367 |
3.533975 |
498.887875 |
75% |
33.711985 |
12.753850 |
37.716432 |
4.126502 |
549.313828 |
max |
36.139662 |
15.126994 |
40.005182 |
6.922689 |
765.518462 |
# Assess the relationship between the time people spend on the website and purchasing
sns.jointplot(x='Time on Website', y='Yearly Amount Spent', data=customers)
<seaborn.axisgrid.JointGrid at 0x1a1ffa9690>
# Assess the relationship between the time people spend on the app and purchasing
sns.jointplot(x='Time on App', y='Yearly Amount Spent', data=customers)
<seaborn.axisgrid.JointGrid at 0x1a2091dbd0>
# Look for any clear correlations
sns.pairplot(customers)
<seaborn.axisgrid.PairGrid at 0x1a2108c7d0>
# Set up independent features as X and the dependent feature as Y
X = customers[['Avg. Session Length', 'Time on App',
'Time on Website', 'Length of Membership']]
y = customers['Yearly Amount Spent']
# Set up my testing and training datasets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)
# Create and train the mobel
lm = LinearRegression()
lm.fit(X_train,y_train)
LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None, normalize=False)
#Create some predictions based on the X test dataset
predictions = lm.predict(X_test)
# Compare our predicitons of Y based on the X test dataset to the actual Y test dataset
ax = sns.scatterplot(y=y_test,x=predictions)
ax.set(xlabel='Y Test', ylabel='Predicted Y')
plt.show()
# Assess the module performance
print('MAE:', metrics.mean_absolute_error(y_test, predictions))
print('MSE:', metrics.mean_squared_error(y_test, predictions))
print('RMSE:', np.sqrt(metrics.mean_squared_error(y_test, predictions)))
MAE: 8.097631371748907
MSE: 104.90160739775463
RMSE: 10.24214857330993
# Evaluate the independent features with the most impact on the purchasing amount of a customer
pd.DataFrame(lm.coef_,X.columns,columns=['Coefficient'])
<style scoped>
.dataframe tbody tr th:only-of-type {
vertical-align: middle;
}
.dataframe tbody tr th {
vertical-align: top;
}
.dataframe thead th {
text-align: right;
}
</style>
|
Coefficient |
Avg. Session Length |
25.745354 |
Time on App |
38.252715 |
Time on Website |
0.894086 |
Length of Membership |
61.575456 |