Data preprocessing

In [11]:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error,r2_score
f=pd.read_csv("Food_Delivery_Times.csv")
f

Out[11]: Order_ID Distance_km Weather Traffic_Level Time_of_Day Vehicle_Type Preparation_Time_min Courier_Experience_yrs Delivery_Time_min

0 522 7.93 Windy Low Afternoon Scooter 12 1.0 43

1 738 16.42 Clear Medium Evening Bike 20 2.0 84

2 741 9.52 Foggy Low Night Scooter 28 1.0 59

3 661 7.44 Rainy Medium Afternoon Scooter 5 1.0 37

4 412 19.03 Clear Low Morning Bike 16 5.0 68

... ... ... ... ... ... ... ... ... ...

995 107 8.50 Clear High Evening Car 13 3.0 54

996 271 16.28 Rainy Low Morning Scooter 8 9.0 71

997 861 15.62 Snowy High Evening Scooter 26 2.0 81

998 436 14.17 Clear Low Afternoon Bike 8 0.0 55

999 103 6.63 Foggy Low Night Scooter 24 3.0 58

1000 rows × 9 columns

In [12]:
f.head()

Out[12]: Order_ID Distance_km Weather Traffic_Level Time_of_Day Vehicle_Type Preparation_Time_min Courier_Experience_yrs Delivery_Time_min

0 522 7.93 Windy Low Afternoon Scooter 12 1.0 43

1 738 16.42 Clear Medium Evening Bike 20 2.0 84

2 741 9.52 Foggy Low Night Scooter 28 1.0 59

3 661 7.44 Rainy Medium Afternoon Scooter 5 1.0 37

4 412 19.03 Clear Low Morning Bike 16 5.0 68

In [13]:
f.describe()

Out[13]: Order_ID Distance_km Preparation_Time_min Courier_Experience_yrs Delivery_Time_min

count 1000.000000 1000.000000 1000.000000 970.000000 1000.000000

mean 500.500000 10.059970 16.982000 4.579381 56.732000

std 288.819436 5.696656 7.204553 2.914394 22.070915

min 1.000000 0.590000 5.000000 0.000000 8.000000

25% 250.750000 5.105000 11.000000 2.000000 41.000000

50% 500.500000 10.190000 17.000000 5.000000 55.500000

75% 750.250000 15.017500 23.000000 7.000000 71.000000

max 1000.000000 19.990000 29.000000 9.000000 153.000000

In [25]:
f.isnull().sum()

Out[25]: Order_ID 0
Distance_km 0
Weather 0
Traffic_Level 0
Time_of_Day 0
Vehicle_Type 0
Preparation_Time_min 0
Courier_Experience_yrs 0
Delivery_Time_min 0
dtype: int64

In [15]:
f.duplicated().sum()

Out[15]: 0

In [16]:
f.shape

Out[16]: (1000, 9)

In [17]:
f.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1000 entries, 0 to 999
Data columns (total 9 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Order_ID 1000 non-null int64
1 Distance_km 1000 non-null float64
2 Weather 970 non-null object
3 Traffic_Level 970 non-null object
4 Time_of_Day 970 non-null object
5 Vehicle_Type 1000 non-null object
6 Preparation_Time_min 1000 non-null int64
7 Courier_Experience_yrs 970 non-null float64
8 Delivery_Time_min 1000 non-null int64
dtypes: float64(2), int64(3), object(4)
memory usage: 70.4+ KB

In [22]:
from sklearn.preprocessing import LabelEncoder
f["Weather"]=LabelEncoder().fit_transform(f["Weather"])
f["Traffic_Level"]=LabelEncoder().fit_transform(f["Traffic_Level"])
f["Time_of_Day"]=LabelEncoder().fit_transform(f["Time_of_Day"])
f["Vehicle_Type"]=LabelEncoder().fit_transform(f["Vehicle_Type"])

In [24]:
f["Courier_Experience_yrs"].fillna(f["Courier_Experience_yrs"].mean(),inplace=True)

visualization
In [40]:
sns.scatterplot(x="Distance_km",y="Delivery_Time_min",data=f)
plt.title("scatter plot of hours studied vs exam score")
plt.xlabel("DISTANCE(KM)")
plt.ylabel("DELIVERY TIME")
plt.show()

In [26]:
correlation=f.corr()
print("correlation Matrix:")
print(correlation)

correlation Matrix:
Order_ID Distance_km Weather Traffic_Level \
Order_ID 1.000000 -0.024483 -0.035785 -0.050845
Distance_km -0.024483 1.000000 0.029756 -0.036602
Weather -0.035785 0.029756 1.000000 -0.031301
Traffic_Level -0.050845 -0.036602 -0.031301 1.000000
Time_of_Day -0.027034 0.009034 0.006595 0.022550
Vehicle_Type -0.045030 0.003319 -0.019231 0.032593
Preparation_Time_min -0.035100 -0.009037 -0.039429 0.004945
Courier_Experience_yrs 0.012933 -0.007713 0.037972 -0.037431
Delivery_Time_min -0.036650 0.780998 0.110254 -0.087523

Time_of_Day Vehicle_Type Preparation_Time_min \

Order_ID -0.027034 -0.045030 -0.035100
Distance_km 0.009034 0.003319 -0.009037
Weather 0.006595 -0.019231 -0.039429
Traffic_Level 0.022550 0.032593 0.004945
Time_of_Day 1.000000 -0.054988 0.004867
Vehicle_Type -0.054988 1.000000 0.020707
Preparation_Time_min 0.004867 0.020707 1.000000
Courier_Experience_yrs -0.057384 -0.002504 -0.030353
Delivery_Time_min 0.025133 -0.006629 0.307350

Courier_Experience_yrs Delivery_Time_min
Order_ID 0.012933 -0.036650
Distance_km -0.007713 0.780998
Weather 0.037972 0.110254
Traffic_Level -0.037431 -0.087523
Time_of_Day -0.057384 0.025133
Vehicle_Type -0.002504 -0.006629
Preparation_Time_min -0.030353 0.307350
Courier_Experience_yrs 1.000000 -0.089066
Delivery_Time_min -0.089066 1.000000

In [28]:
x=f[["Distance_km"]]
y=f["Delivery_Time_min"]
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=42)

In [29]:
model=LinearRegression()
model.fit(x_train,y_train)

Out[29]: LinearRegression()

In [30]:
print("\nModel coeeficient:")
print(f"Intercept:{model.intercept_}")
print(f"slope:{model.coef_[0]}")

Model coeeficient:
Intercept:26.585748176869693
slope:3.0164695806793005

In [31]:
y_pred=model.predict(x_test)

Evaluation metrics and interpretation

In [38]:
from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score

mse = mean_squared_error(y_test, y_pred)

r2 = r2_score(y_test, y_pred)
mae = mean_absolute_error(y_test, y_pred)
print("\nModel Evaluation:")
print(f"Mean Squared Error (MSE): {mse}")
print(f"R-squared (R2): {r2}")
print(f"Mean Absolute Error (MAE): {mae}")

Model Evaluation:
Mean Squared Error (MSE): 158.16196727280166
R-squared (R2): 0.6471386683659509
Mean Absolute Error (MAE): 9.580954148917813

INTERPRETING R2
In [42]:
if r2==1:
print("THE MODEL PERFECTLY EXPLAINS THE VARIANCE IN SALES REVENUE")
elif r2>0.5:
print("THE MODEL EXPLAINS A MODERATE PROPORTION OF THE VARIANCE IN SALES REVENUE")
elif r2>0.8:
print("THE MODEL EXPLAINS A STRONG PROPORTION OF THE VARIANCE IN SALES REVENUE")
elif r2>0.5:
print("THE MODEL EXPLAINS A MODERATE PROPORTION OF THE VARIANCE IN SALES REVENUE")
else:
print("THE MODEL EXPLAINS A WEAK PROPORTION OF THE VARIANCE IN SALES REVENUE")

THE MODEL EXPLAINS A MODERATE PROPORTION OF THE VARIANCE IN SALES REVENUE

In [33]:
plt.scatter(x, y, color="blue", label="Data Points")
plt.plot(x, model.predict(x), color="red", label="Regression Line")
plt.title("Simple Linear Regression: Hours Studied vs Exam Score")
plt.xlabel("Hours Studied")
plt.ylabel("Exam Score")
plt.legend()
plt.show()

In [ ]: