Electric Vehicles

DataFrameas

df

variable

SELECT *
FROM VEHICLES.CHARGING_SESSIONS

import packages

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

df.info()

garage_id: Identifies the garage where the charging took place.

user_id: Identifies the user.

user_type: Describes the type of user (e.g., private).

start_plugin: The timestamp of when the charging session began.

start_plugin_hour: The hour of the day when the charging session started.

end_plugout: The timestamp of when the charging session ended.

end_plugout_hour: The hour of the day when the charging session ended.

el_kwh: The amount of electricity used during the charging session in kWh.

duration_hours: The duration of the charging session in hours.

month_plugin: The month the charging session started.

weekdays_plugin: The day of the week when the charging occurred.

null values check

# Check for missing values
print(df.isnull().sum())

unique values

# Get the count of unique values in each column
unique_counts = df.nunique()
unique_counts

missing value treatment

# Drop rows with missing values
data = df.dropna()

# Display the first few rows of the cleaned dataframe to verify
data.info()

data set numerical values describe

data.describe()

feature enginerring

# Convert 'start_plugin' to datetime for better handling
data['start_plugin'] = pd.to_datetime(data['start_plugin'])
data['end_plugout'] = pd.to_datetime(data['end_plugout'])

‌
‌
‌