PA Exp 2 Predicting buying customer_behaviour and Predict customer ... https://colab.research.google.com/drive/18ImfExgc2pyWKWnkMoEi...

1 #Random Forest Classification, decision tree classification

1 import numpy as np
2 import matplotlib.pyplot as plt
3 import pandas as pd

1 df = pd.read_csv('car_data.csv')

1 display(df.head(5))

User ID Gender Age AnnualSalary Purchased

0 385 Male 35 20000 0

1 681 Male 40 43500 0

2 353 Male 49 74000 0

3 895 Male 40 107500 1

4 661 Male 25 79000 0

1 X = df.iloc[:400, [2,3]].values
2 y = df.iloc[:400, -1].values

1 of 11 21-09-2023, 13:01
PA Exp 2 Predicting buying customer_behaviour and Predict customer ... https://colab.research.google.com/drive/18ImfExgc2pyWKWnkMoEi...

3 print(X)

[[ 35 20000]
[ 40 43500]
[ 49 74000]
[ 40 107500]
[ 25 79000]
[ 47 33500]
[ 46 132500]
[ 42 64000]
[ 30 84500]
[ 41 52000]
[ 42 80000]
[ 47 23000]
[ 32 72500]
[ 27 57000]
[ 42 108000]
[ 33 149000]
[ 35 75000]
[ 35 53000]
[ 46 79000]
[ 39 134000]
[ 39 51500]
[ 49 39000]
[ 54 25500]
[ 41 61500]
[ 31 117500]
[ 24 58000]
[ 40 107000]
[ 40 97500]
[ 48 29000]
[ 38 147500]
[ 45 26000]
[ 32 67500]
[ 37 62000]
[ 41 79500]
[ 44 113500]
[ 47 41500]
[ 38 55000]
[ 39 114500]
[ 42 73000]
[ 26 15000]
[ 21 37500]
[ 59 39500]
[ 39 66500]
[ 43 80500]
[ 49 86000]
[ 37 75000]
[ 49 76500]
[ 28 123000]
[ 59 48500]
[ 40 60500]
[ 38 99500]
[ 51 35500]
[ 55 130000]
[ 23 56500]

2 of 11 21-09-2023, 13:01
PA Exp 2 Predicting buying customer_behaviour and Predict customer ... https://colab.research.google.com/drive/18ImfExgc2pyWKWnkMoEi...

[ 23 56500]
[ 49 43500]
[ 49 36000]
[ 48 21500]
[ 49 98500]

1 sampled_df = df.sample(n=400)
2 X = sampled_df.iloc[:, [2,3]].values
3 y = sampled_df.iloc[:, -1].values
4 print(X)

[[ 22 55000]
[ 26 23500]
[ 46 23000]
[ 26 35000]
[ 43 63500]
[ 30 62500]
[ 38 63500]
[ 36 21500]
[ 50 37500]
[ 38 72500]
[ 33 69000]
[ 32 86000]
[ 32 35500]
[ 51 45500]
[ 20 74000]
[ 38 74500]
[ 29 60500]
[ 35 22000]
[ 44 73500]
[ 35 47000]
[ 26 80500]
[ 35 57000]
[ 35 79000]
[ 57 61500]
[ 40 123500]
[ 45 82500]
[ 28 138500]
[ 32 72500]
[ 30 76500]
[ 38 65000]
[ 49 36500]
[ 20 86500]
[ 40 97500]
[ 36 51500]
[ 39 52500]
[ 25 90000]
[ 25 56500]
[ 26 17000]
[ 59 135500]
[ 49 119500]
[ 34 72000]
[ 28 59000]
[ 52 67500]
[ 50 45500]

3 of 11 21-09-2023, 13:01
PA Exp 2 Predicting buying customer_behaviour and Predict customer ... https://colab.research.google.com/drive/18ImfExgc2pyWKWnkMoEi...

[ 50 45500]
[ 40 148500]
[ 48 114500]
[ 20 77500]
[ 29 45500]
[ 26 118000]
[ 31 108500]
[ 41 60000]
[ 39 42000]
[ 59 42000]
[ 40 82500]
[ 60 124500]
[ 31 90500]
[ 51 35500]
[ 50 107500]

1 #splitting the dataset into the Training set and Test set
2 from sklearn.model_selection import train_test_split
3 X_train, X_test, y_train, y_test = train_test_split(X,y, test_size = 0.25, random_state =

1 #feature scaling
2 from sklearn.linear_model import LogisticRegression
3 from sklearn.preprocessing import StandardScaler
4 classifier = LogisticRegression()
5 sc = StandardScaler()
6 X_train = sc.fit_transform(X_train)
7 X_test = sc.transform(X_test)
8 y_train = y_train.ravel()
9 classifier.fit(X_train, y_train)

▾ LogisticRegression
LogisticRegression()

1 print(X_train)

[[ 1.85560654 2.30625342]
[ 0.41442093 -0.17358897]
[ 0.89481613 0.13639133]
[ 0.99089517 -0.14259094]
[-0.06597427 0.18288838]
[ 0.51049997 -0.45257124]
[-1.3150018 0.3068805 ]
[ 0.89481613 -0.99503676]
[ 0.89481613 1.99627313]
[-0.3542114 -0.79354957]
[-1.3150018 -1.21202297]
[ 0.12618381 0.24488444]
[ 0.03010477 1.11282927]
[-0.45029044 -0.43707222]
[ 0.41442093 -0.5145673 ]
[ 0.79873709 -1.13452789]
[ 1.08697421 -1.53750228]

4 of 11 21-09-2023, 13:01
PA Exp 2 Predicting buying customer_behaviour and Predict customer ... https://colab.research.google.com/drive/18ImfExgc2pyWKWnkMoEi...

[ 1.08697421 -1.53750228]
[-0.8346066 1.15932632]
[-1.41108084 0.44637163]
[ 0.31834189 0.29138148]
[-0.3542114 2.39924751]
[ 0.22226285 -0.54556533]
[ 0.03010477 0.16738936]
[-0.06597427 -1.10352986]
[ 0.31834189 -0.48356927]
[ 0.03010477 0.04339724]
[-0.45029044 0.24488444]
[ 0.60657901 -1.47550622]
[-1.12284372 -1.53750228]
[ 0.70265805 -1.16552592]
[-2.08363413 -0.09609389]
[-0.06597427 0.04339724]
[-1.21892276 0.52386671]
[ 0.03010477 1.99627313]
[ 0.22226285 -0.57656336]
[-0.3542114 -0.32857912]
[ 0.99089517 0.57036375]
[ 0.70265805 -0.32857912]
[-1.89147604 0.33787853]
[-0.45029044 -1.52200327]
[-0.93068564 0.4153736 ]
[-1.21892276 0.39987459]
[ 0.89481613 -1.07253183]
[ 1.18305325 0.16738936]
[ 0.51049997 -0.80904858]
[-0.93068564 -0.8245476 ]
[-1.3150018 0.27588247]
[ 0.79873709 -1.18102494]
[ 0.22226285 -0.18908798]
[-0.25813236 0.21388641]
[-0.06597427 -0.45257124]
[ 0.12618381 -0.39057518]
[ 2.2399227 -0.8245476 ]
[ 0.03010477 0.29138148]
[ 0.03010477 2.12026525]
[-1.50715988 -1.36701312]
[-0.3542114 0.66335784]
[-0.8346066 -0.40607419]

1 print(classifier.predict(sc.transform([[49, 74000]])))

[1]

1 y_pred = classifier.predict(X_test)
2 print(np.concatenate((y_pred.reshape(len(y_pred),1), y_test.reshape(len(y_test),1)),1))

[[0 0]
[0 0]
[1 1]
[0 1]

5 of 11 21-09-2023, 13:01
PA Exp 2 Predicting buying customer_behaviour and Predict customer ... https://colab.research.google.com/drive/18ImfExgc2pyWKWnkMoEi...

[0 0]
[1 1]
[1 1]
[1 1]
[0 0]
[0 1]
[0 0]
[1 1]
[1 1]
[1 1]
[0 0]
[1 1]
[0 1]
[0 0]
[1 1]
[0 0]
[1 1]
[1 1]
[1 1]
[1 1]
[0 0]
[0 0]
[0 0]
[0 0]
[1 1]
[0 0]
[0 0]
[1 0]
[0 0]
[1 1]
[0 0]
[0 0]
[0 0]
[0 0]
[1 1]
[1 1]
[0 0]
[0 0]
[0 0]
[0 0]
[1 1]
[1 1]
[0 0]
[0 1]
[1 0]
[1 1]
[0 1]
[1 1]
[0 0]
[0 0]
[0 0]
[0 0]
[1 0]
[0 0]

6 of 11 21-09-2023, 13:01
PA Exp 2 Predicting buying customer_behaviour and Predict customer ... https://colab.research.google.com/drive/18ImfExgc2pyWKWnkMoEi...

1 import seaborn as sns

2 import matplotlib.pyplot as plt
3 from sklearn.metrics import confusion_matrix
4 from sklearn.metrics import plot_confusion_matrix
5 from sklearn.metrics import accuracy_score
6 cm = confusion_matrix(y_test, y_pred)
7 sns.heatmap(cm, annot=True, fmt='g')
8 plt.xlabel('Predicted labels')
9 plt.ylabel('True labels')
10 plt.show()
11
12 accuracy = accuracy_score(y_test, y_pred)
13 print(cm)
14 print(f'Accuracy: {accuracy:.3f}')
15
16

---------------------------------------------------------------------------
ImportError Traceback (most recent call last)
<ipython-input-24-2a6c70da7013> in <module>
2 import matplotlib.pyplot as plt
3 from sklearn.metrics import confusion_matrix
----> 4 from sklearn.metrics import plot_confusion_matrix
5 from sklearn.metrics import accuracy_score
6 cm = confusion_matrix(y_test, y_pred)

ImportError: cannot import name 'plot_confusion_matrix' from 'sklearn.metrics'

(/usr/local/lib/python3.9/dist-packages/sklearn/metrics/__init__.py)

---------------------------------------------------------------------------
NOTE: If your import is failing due to a missing package, you can
manually install dependencies using either !pip or !apt.

To view examples of installing some common dependencies, click the

"Open Examples" button below.
---------------------------------------------------------------------------

7 of 11 21-09-2023, 13:01
PA Exp 2 Predicting buying customer_behaviour and Predict customer ... https://colab.research.google.com/drive/18ImfExgc2pyWKWnkMoEi...

1 from matplotlib.colors import ListedColormap

2 X_set, y_set = sc.inverse_transform(X_train), y_train
3 X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 10, stop = X_set[:, 0].max() +
4 np.arange(start = X_set[:, 1].min() - 1000, stop = X_set[:, 1].max() +
5 plt.contourf(X1, X2, classifier.predict(sc.transform(np.array([X1.ravel(), X2.ravel()]).T)).re
6 alpha = 0.75, cmap = ListedColormap(('slategrey', 'slateblue')))
7 plt.xlim(X1.min(), X1.max())
8 plt.ylim(X2.min(), X2.max())
9 for i, j in enumerate(np.unique(y_set)):
10 plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1], color = ListedColormap(('slategrey
11 plt.title('Random Forest Classification (Train set)')
12 plt.xlabel('Age')
13 plt.ylabel('Estimated Salary')
14 plt.legend()
15 plt.show()

8 of 11 21-09-2023, 13:01
PA Exp 2 Predicting buying customer_behaviour and Predict customer ... https://colab.research.google.com/drive/18ImfExgc2pyWKWnkMoEi...

1 from matplotlib.colors import ListedColormap

2 X_set, y_set = sc.inverse_transform(X_test), y_test
3 X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 10, stop = X_set[:, 0].max() +
4 np.arange(start = X_set[:, 1].min() - 1000, stop = X_set[:, 1].max() +
5 plt.contourf(X1, X2, classifier.predict(sc.transform(np.array([X1.ravel(), X2.ravel()]).T)).re
6 alpha = 0.75, cmap = ListedColormap(('slategrey', 'slateblue')))
7 plt.xlim(X1.min(), X1.max())
8 plt.ylim(X2.min(), X2.max())
9 for i, j in enumerate(np.unique(y_set)):
10 plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1], color = ListedColormap(('slategrey
11 plt.title('Random Forest Classification (Test set)')
12 plt.xlabel('Age')
13 plt.ylabel('Estimated Salary')
14 plt.legend()
15 plt.show()

1 # create a new data point to predict

2 new_data = [[35, 50000]]
3
4 # scale the new data using the same scaler used on the training data
5 new_data_scaled = sc.transform(new_data)
6
7 # make a prediction using the trained classifier
8 prediction = classifier.predict(new_data_scaled)

9 of 11 21-09-2023, 13:01
PA Exp 2 Predicting buying customer_behaviour and Predict customer ... https://colab.research.google.com/drive/18ImfExgc2pyWKWnkMoEi...

9
10 print(prediction)
11

[0]

1 new_data_2 = [[35, 50000], [42, 80700], [51, 65000], [23, 45600], [36, 42000], [41, 72000
2 df = pd.DataFrame(new_data_2, columns=[ 'Age', 'Annual Salary'])
3 df.index = df.index + 1
4 display(df)
5

Age Annual Salary

1 35 50000

2 42 80700

3 51 65000

4 23 45600

5 36 42000

6 41 72000

1 from tabulate import tabulate

2
3 results = []
4
5 for i, data in enumerate(new_data_2):
6 # scale the new data using the same scaler used on the training data
7 data_scaled = sc.transform([data])
8
9 # make a prediction using the trained classifier
10 prediction = classifier.predict(data_scaled)
11
12 # add the results to the table
13 if prediction == 1:
14 prediction_text = "Yes"
15 else:
16 prediction_text = "No"
17 results.append([i+1, data[0], data[1], prediction_text])
18
19 # print the table

10 of 11 21-09-2023, 13:01
PA Exp 2 Predicting buying customer_behaviour and Predict customer ... https://colab.research.google.com/drive/18ImfExgc2pyWKWnkMoEi...

20 headers = ["Customer", "Age", "Annual Salary", "Prediction"]

21 print(tabulate(results, headers=headers))
22

Customer Age Annual Salary Prediction

---------- ----- --------------- ------------
1 35 50000 No
2 42 80700 No
3 51 65000 Yes
4 23 45600 No
5 36 42000 No
6 41 72000 No

11 of 11 21-09-2023, 13:01