User Behavior Exploration Analysis

#Import Pandas and Matplotlib
import pandas as pd 
import plotly.express as px

from IPython.display import display, Markdown

#Read CSV and anaylize table
data = pd.read_csv('userbehaviour.csv')

print(data.info())
print(data.head())

Hidden output

data.rename(columns={"Average Spent on App (INR)": "Average Spent on App (USD)"}, inplace=True)

#Highest, lowest, and AVG screen time(minutes)
print(f'Highest Screen Time = {data["Average Screen Time"].max()}')
print(f'Lowest Screen Time = {data["Average Screen Time"].min()}')
print(f'Average Screen Time = {data["Average Screen Time"].mean()}')

#Highest, lowest, and AVG spend(dollars)
print(f'Highest User Spend = {data["Average Spent on App (USD)"].max()}')
print(f'Lowest User Spend = {data["Average Spent on App (USD)"].min()}')
print(f'Average User Spend = {data["Average Spent on App (USD)"].mean()}')

figure = px.scatter(data_frame = data, 
                    x="Average Screen Time",
                    y="Ratings", 
                    size ="Ratings",
                    color= "Status",
                    title = "Correlation Between Ratings and Screentime",
                    trendline="ols")
figure.show()

figure = px.scatter(data_frame = data, 
                    x="Average Screen Time",
                    y="Average Spent on App (USD)", 
                    size="Average Spent on App (USD)", 
                    color= "Status",
                    title = "Correlation Between Average Spending and Screentime",
                    trendline="ols")
figure.show()

#Find Churn
churn = (data['Status'].values == 'Uninstalled').sum()
print(churn)

#Find Total Users
tot_users = (data['userid']).count()
print(tot_users)

#Find Churn Rate
churn_rate = churn/tot_users
print(churn_rate)