# This Python 3 environment comes with many helpful analytics libraries installed

# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python

# For example, here's several helpful packages to load

import numpy as np # linear algebra

import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)

# Input data files are available in the read-only "../input/" directory

# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory

import os
for dirname, _, filenames in os.walk('/kaggle/input'):
for filename in filenames:
print(os.path.join(dirname, filename))

# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create
# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session

/kaggle/input/air-quality-and-pollution-assessment/pollution_dataset.csv

Libraries
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
import matplotlib.pyplot as plt
import seaborn as sns

Data Upload
df=pd.read_csv('/kaggle/input/air-quality-and-pollution-assessment/pollution_dataset.csv').dropna()

df.head(3)

Temperature Humidity PM2.5 PM10 NO2 SO2 CO Proximity_to_Industrial_Areas Population_Density Air Quality

0 27.2 51.7 35.1 46.2 26.7 32.2 0.98 11.2 314 Hazardous

1 26.3 59.3 1.0 6.2 38.3 20.4 0.68 13.5 298 Good

2 27.9 73.2 20.0 39.4 19.6 5.8 0.95 5.4 309 Good

Data Preprocessing
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 5000 entries, 0 to 4999
Data columns (total 10 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Temperature 5000 non-null float64
1 Humidity 5000 non-null float64
2 PM2.5 5000 non-null float64
3 PM10 5000 non-null float64
4 NO2 5000 non-null float64
5 SO2 5000 non-null float64
6 CO 5000 non-null float64
7 Proximity_to_Industrial_Areas 5000 non-null float64
8 Population_Density 5000 non-null int64
9 Air Quality 5000 non-null object
dtypes: float64(8), int64(1), object(1)
memory usage: 390.8+ KB

df['Air Quality'].unique()

array(['Hazardous', 'Good', 'Poor', 'Moderate'], dtype=object)

ENCODİNG
custom_mapping = {'Hazardous': 0, 'Poor': 1, 'Moderate': 2, 'Good': 3}
 df['Air Quality'] = df['Air Quality'].map(custom_mapping)

print("Updated DataFrame:")
print(df)

Updated DataFrame:
Temperature Humidity PM2.5 PM10 NO2 SO2 CO \
0 27.2 51.7 35.1 46.2 26.7 32.2 0.98
1 26.3 59.3 1.0 6.2 38.3 20.4 0.68
2 27.9 73.2 20.0 39.4 19.6 5.8 0.95
3 23.9 51.9 14.7 24.3 5.2 12.6 1.24
4 25.2 59.0 26.3 30.9 26.8 13.5 1.06
... ... ... ... ... ... ... ...
4995 29.3 36.8 80.3 90.9 9.2 14.1 0.97
4996 15.7 51.7 0.7 11.4 40.5 13.8 1.07
4997 27.8 48.1 8.9 16.4 8.6 17.7 0.54
4998 30.4 50.4 2.2 18.8 13.1 22.3 0.94
4999 21.5 76.5 45.0 58.0 37.9 0.0 0.96

Proximity_to_Industrial_Areas Population_Density Air Quality

0 11.2 314 0
1 13.5 298 3
2 5.4 309 3
3 4.5 282 1
4 5.6 293 1
... ... ... ...
4995 10.2 287 2
4996 4.2 320 3
4997 0.3 302 2
4998 6.7 308 2
4999 0.2 290 0

[5000 rows x 10 columns]

#Hazardous -> 0
#Poor -> 1
#Moderate -> 2
#Good -> 3

df.head(3)

Temperature Humidity PM2.5 PM10 NO2 SO2 CO Proximity_to_Industrial_Areas Population_Density Air Quality

0 27.2 51.7 35.1 46.2 26.7 32.2 0.98 11.2 314 0

1 26.3 59.3 1.0 6.2 38.3 20.4 0.68 13.5 298 3

2 27.9 73.2 20.0 39.4 19.6 5.8 0.95 5.4 309 3

Train-Test
y=df["Air Quality"]
x=df.drop("Air Quality", axis=1)

x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.33, random_state=42)

scaler = StandardScaler()

Standard Scaler
x_train_scaled = scaler.fit_transform(x_train)
x_test_scaled = scaler.transform(x_test)

df.head(3)

Temperature Humidity PM2.5 PM10 NO2 SO2 CO Proximity_to_Industrial_Areas Population_Density Air Quality

0 27.2 51.7 35.1 46.2 26.7 32.2 0.98 11.2 314 0

1 26.3 59.3 1.0 6.2 38.3 20.4 0.68 13.5 298 3

2 27.9 73.2 20.0 39.4 19.6 5.8 0.95 5.4 309 3

Random Forest
 clf = RandomForestClassifier(random_state=42)
clf.fit(x_train_scaled, y_train)

▾ RandomForestClassifier

RandomForestClassifier(random_state=42)

Predict
y_pred = clf.predict(x_test_scaled)
print(classification_report(y_test, y_pred))

precision recall f1-score support

0 0.00 0.00 0.00 174

1 0.18 0.04 0.07 309
2 0.33 0.28 0.30 516
3 0.39 0.69 0.50 651

accuracy 0.37 1650

macro avg 0.23 0.25 0.22 1650
weighted avg 0.29 0.37 0.31 1650

accuracy = accuracy_score(y_test, y_pred)

print(f"Accuracy: {accuracy:.2f}")
print("\nClassification Report:\n", classification_report(y_test, y_pred))

Accuracy: 0.37

Classification Report:
precision recall f1-score support

0 0.00 0.00 0.00 174

1 0.18 0.04 0.07 309
2 0.33 0.28 0.30 516
3 0.39 0.69 0.50 651

accuracy 0.37 1650

macro avg 0.23 0.25 0.22 1650
weighted avg 0.29 0.37 0.31 1650

Data Visualization
import warnings
warnings.filterwarnings('ignore')

sns.pairplot(df, hue='Air Quality', palette='Set1', diag_kind='kde')

plt.suptitle('Pairplot of Features vs Air Quality', y=1.02)
plt.show()
cm = confusion_matrix(y_test, y_pred)
plt.figure(figsize=(8, 6))
sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', xticklabels=clf.classes_, yticklabels=clf.classes_)
plt.title('Confusion Matrix')
plt.xlabel('Predicted')
plt.ylabel('Actual')
plt.show()
"Thank you for exploring this notebook! I hope you found the analysis insightful and informative. Feel free to share your thoughts and
questions in the comments below!"