Ilovepdf Merged

Name : ____Siddhant Mandal________ Subject: Machine Learning
Class: MSC-II (Artificial intelligence) Exam Seat no: _3269587_____
Academic Year: 2022-2023
INDEX
No Date TITLE Page SIGN

No
1
Implementation of Simple Linear Regression.
2
Implementation of Multiple Linear Regression.
3
Implementation of Support Vector Regression.
4
Implementation of Naïve Bayes Classifier.
5
Implementation of Decision Tree Classifier.
6
Implementation of Adaboost for Naïve Bayes Classifier.
7
Implementation of Adaboost for Decision Tree Classifier.
8
Implementation of Artificial Neural Network.
9 Implementation of hierarchical clustering

1/23/23, 2:33 AM Untitled34.ipynb - Colaboratory
Executed by Siddhant Mandal
University Department of Information Technology
D.G. Ruparel College
Msc.IT Part 2 Sem 3
Subject = Machine Learning
Practical 1 : Implementation of Simple Linear Regression
Importing the Libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
Importing the dataset
dataset = pd.read_csv('/content/sample_data/Salary_Data.csv')
X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, -1].values
print(X)
[[ 1.1]
[ 1.3]
[ 1.5]
[ 2. ]
[ 2.2]
[ 2.9]
[ 3. ]
[ 3.2]
[ 3.2]
[ 3.7]
[ 3.9]
[ 4. ]
[ 4. ]
[ 4.1]
[ 4.5]
[ 4.9]
[ 5.1]
[ 5.3]
[ 5.9]
[ 6. ]
[ 6.8]
[ 7.1]
[ 7.9]
[ 8.2]
[ 8.7]
[ 9. ]
[ 9.5]
[ 9.6]
[10.3]
[10.5]]
print(y)
[ 39343. 46205. 37731. 43525. 39891. 56642. 60150. 54445. 64445.

57189. 63218. 55794. 56957. 57081. 61111. 67938. 66029. 83088.
81363. 93940. 91738. 98273. 101302. 113812. 109431. 105582. 116969.
112635. 122391. 121872.]
Splitting the dataset into the Training Set and Test Set
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 1/3, random_state = 0)
https://colab.research.google.com/drive/1_fY-ZsE19bsvDSsXkKoJmJWkDE19Di8v#scrollTo=WhFN4cj_Rh3R&printMode=true 1/3
print(X_train)
[[ 2.9]
[ 5.1]
[ 3.2]
[ 4.5]
[ 8.2]
[ 6.8]
[ 1.3]
[10.5]
[ 3. ]
[ 2.2]
[ 5.9]
[ 6. ]
[ 3.7]
[ 3.2]
[ 9. ]
[ 2. ]
[ 1.1]
[ 7.1]
[ 4.9]
[ 4. ]]
print(X_test)
[[ 1.5]
[10.3]
[ 4.1]
[ 3.9]
[ 9.5]
[ 8.7]
[ 9.6]
[ 4. ]
[ 5.3]
[ 7.9]]
print(y_train)
[ 56642. 66029. 64445. 61111. 113812. 91738. 46205. 121872. 60150.

39891. 81363. 93940. 57189. 54445. 105582. 43525. 39343. 98273.
67938. 56957.]
print(y_test)
[ 37731. 122391. 57081. 63218. 116969. 109431. 112635. 55794. 83088.

101302.]
Training the Simple Linear Regression Model on the Training Set
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train, y_train)
LinearRegression()
Predicting the Test Set Result
y_pred = regressor.predict(X_test)
Visualizing the Training Set Results
plt.scatter(X_train, y_train, color = 'red')
plt.plot(X_train, regressor.predict(X_train), color = 'blue')
plt.title('Salary vs Experience (Training set)')
plt.xlabel('Years of Experience')
plt.ylabel('Salary')
plt.show()
Visualizing the Test Set Results
plt.scatter(X_test, y_test, color = 'red')
plt.plot(X_test, regressor.predict(X_test), color = 'blue')
plt.title('Salary vs Experience (Test set)')
plt.xlabel('Years of Experience')
plt.ylabel('Salary')
plt.show()
Colab paid products - Cancel contracts here
check 0s completed at 2:20 AM
Msc.IT Part 2 Sem 3
Practical 2 : Implementation of Multiple Linear Regression.
Importing the Libraries
import numpy as np
import pandas as pd
dataset = pd.read_csv('/content/sample_data/50_Startups.csv')
print(X)
[[165349.2 136897.8 471784.1 'New York']

[162597.7 151377.59 443898.53 'California']
[153441.51 101145.55 407934.54 'Florida']
[144372.41 118671.85 383199.62 'New York']
[142107.34 91391.77 366168.42 'Florida']
[131876.9 99814.71 362861.36 'New York']
[134615.46 147198.87 127716.82 'California']
[130298.13 145530.06 323876.68 'Florida']
[120542.52 148718.95 311613.29 'New York']
[123334.88 108679.17 304981.62 'California']
[101913.08 110594.11 229160.95 'Florida']
[100671.96 91790.61 249744.55 'California']
[93863.75 127320.38 249839.44 'Florida']
[91992.39 135495.07 252664.93 'California']
[119943.24 156547.42 256512.92 'Florida']
[114523.61 122616.84 261776.23 'New York']
[78013.11 121597.55 264346.06 'California']
[94657.16 145077.58 282574.31 'New York']
[91749.16 114175.79 294919.57 'Florida']
[86419.7 153514.11 0.0 'New York']
[76253.86 113867.3 298664.47 'California']
[78389.47 153773.43 299737.29 'New York']
[73994.56 122782.75 303319.26 'Florida']
[67532.53 105751.03 304768.73 'Florida']
[77044.01 99281.34 140574.81 'New York']
[64664.71 139553.16 137962.62 'California']
[75328.87 144135.98 134050.07 'Florida']
[72107.6 127864.55 353183.81 'New York']
[66051.52 182645.56 118148.2 'Florida']
[65605.48 153032.06 107138.38 'New York']
[61994.48 115641.28 91131.24 'Florida']
[61136.38 152701.92 88218.23 'New York']
[63408.86 129219.61 46085.25 'California']
[55493.95 103057.49 214634.81 'Florida']
[46426.07 157693.92 210797.67 'California']
[46014.02 85047.44 205517.64 'New York']
[28663.76 127056.21 201126.82 'Florida']
[44069.95 51283.14 197029.42 'California']
[20229.59 65947.93 185265.1 'New York']
[38558.51 82982.09 174999.3 'California']
[28754.33 118546.05 172795.67 'California']
[27892.92 84710.77 164470.71 'Florida']
[23640.93 96189.63 148001.11 'California']
[15505.73 127382.3 35534.17 'New York']
[22177.74 154806.14 28334.72 'California']
[1000.23 124153.04 1903.93 'New York']
[1315.46 115816.21 297114.46 'Florida']
[0.0 135426.92 0.0 'California']
https://colab.research.google.com/drive/1_fY-ZsE19bsvDSsXkKoJmJWkDE19Di8v#scrollTo=4STz9XIyRbR8&printMode=true 1/3
[542.05 51743.15 0.0 'New York']
[0.0 116983.8 45173.06 'California']]
print(y)
[192261.83 191792.06 191050.39 182901.99 166187.94 156991.12 156122.51

155752.6 152211.77 149759.96 146121.95 144259.4 141585.52 134307.35
132602.65 129917.04 126992.93 125370.37 124266.9 122776.86 118474.03
111313.02 110352.25 108733.99 108552.04 107404.34 105733.54 105008.31
103282.38 101004.64 99937.59 97483.56 97427.84 96778.92 96712.8
96479.51 90708.19 89949.14 81229.06 81005.76 78239.91 77798.83
71498.49 69758.98 65200.33 64926.08 49490.75 42559.73 35673.41
14681.4 ]
Encoding Categorical Data
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder
ct = ColumnTransformer(transformers=[('encoder', OneHotEncoder(), [3])], remainder='passthrough')
X = np.array(ct.fit_transform(X))
print(X)
[[0.0 0.0 1.0 165349.2 136897.8 471784.1]

[1.0 0.0 0.0 162597.7 151377.59 443898.53]
[0.0 1.0 0.0 153441.51 101145.55 407934.54]
[0.0 0.0 1.0 144372.41 118671.85 383199.62]
[0.0 1.0 0.0 142107.34 91391.77 366168.42]
[0.0 0.0 1.0 131876.9 99814.71 362861.36]
[1.0 0.0 0.0 134615.46 147198.87 127716.82]
[0.0 1.0 0.0 130298.13 145530.06 323876.68]
[0.0 0.0 1.0 120542.52 148718.95 311613.29]
[1.0 0.0 0.0 123334.88 108679.17 304981.62]
[0.0 1.0 0.0 101913.08 110594.11 229160.95]
[1.0 0.0 0.0 100671.96 91790.61 249744.55]
[0.0 1.0 0.0 93863.75 127320.38 249839.44]
[1.0 0.0 0.0 91992.39 135495.07 252664.93]
[0.0 1.0 0.0 119943.24 156547.42 256512.92]
[0.0 0.0 1.0 114523.61 122616.84 261776.23]
[1.0 0.0 0.0 78013.11 121597.55 264346.06]
[0.0 0.0 1.0 94657.16 145077.58 282574.31]
[0.0 1.0 0.0 91749.16 114175.79 294919.57]
[0.0 0.0 1.0 86419.7 153514.11 0.0]
[1.0 0.0 0.0 76253.86 113867.3 298664.47]
[0.0 0.0 1.0 78389.47 153773.43 299737.29]
[0.0 1.0 0.0 73994.56 122782.75 303319.26]
[0.0 1.0 0.0 67532.53 105751.03 304768.73]
[0.0 0.0 1.0 77044.01 99281.34 140574.81]
[1.0 0.0 0.0 64664.71 139553.16 137962.62]
[0.0 1.0 0.0 75328.87 144135.98 134050.07]
[0.0 0.0 1.0 72107.6 127864.55 353183.81]
[0.0 1.0 0.0 66051.52 182645.56 118148.2]
[0.0 0.0 1.0 65605.48 153032.06 107138.38]
[0.0 1.0 0.0 61994.48 115641.28 91131.24]
[0.0 0.0 1.0 61136.38 152701.92 88218.23]
[1.0 0.0 0.0 63408.86 129219.61 46085.25]
[0.0 1.0 0.0 55493.95 103057.49 214634.81]
[1.0 0.0 0.0 46426.07 157693.92 210797.67]
[0.0 0.0 1.0 46014.02 85047.44 205517.64]
[0.0 1.0 0.0 28663.76 127056.21 201126.82]
[1.0 0.0 0.0 44069.95 51283.14 197029.42]
[0.0 0.0 1.0 20229.59 65947.93 185265.1]
[1.0 0.0 0.0 38558.51 82982.09 174999.3]
[1.0 0.0 0.0 28754.33 118546.05 172795.67]
[0.0 1.0 0.0 27892.92 84710.77 164470.71]
[1.0 0.0 0.0 23640.93 96189.63 148001.11]
[0.0 0.0 1.0 15505.73 127382.3 35534.17]
[1.0 0.0 0.0 22177.74 154806.14 28334.72]
[0.0 0.0 1.0 1000.23 124153.04 1903.93]
[0.0 1.0 0.0 1315.46 115816.21 297114.46]
[1.0 0.0 0.0 0.0 135426.92 0.0]
[0.0 0.0 1.0 542.05 51743.15 0.0]
[1.0 0.0 0.0 0.0 116983.8 45173.06]]
Splitting the dataset into the Training Set and Test Set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)
Training the Multiple Linear Regression Model on the Training Set
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train, y_train)
LinearRegression()
Predicting the Test Set Results
y_pred = regressor.predict(X_test)
np.set_printoptions(precision=2)
print(np.concatenate((y_pred.reshape(len(y_pred),1), y_test.reshape(len(y_test),1)),1))
[[103015.2 103282.38]
[132582.28 144259.4 ]
[132447.74 146121.95]
[ 71976.1 77798.83]
[178537.48 191050.39]
[116161.24 105008.31]
[ 67851.69 81229.06]
[ 98791.73 97483.56]
[113969.44 110352.25]
[167921.07 166187.94]]

Msc.IT Part 2 Sem 3
Practical 3 : Implementation of Support Vector Regression.
Step 1 :Importing the Libraries
import numpy as np
import pandas as pd
step 2: Reading the dataset
dataset = pd.read_csv('/content/sample_data/Position_Salaries.csv')
X = dataset.iloc[:, 1:2].values
y·=·dataset.iloc[:,·2].values
print(X)
print(y)
[[ 1]
[ 2]
[ 3]
[ 4]
[ 5]
[ 6]
[ 7]
[ 8]
[ 9]
[10]]
[ 45000 50000 60000 80000 110000 150000 200000 300000 500000
1000000]
Step 3: Feature Scaling
A real-world dataset contains features that vary in magnitudes, units, and range. I would suggest
performing normalization when the scale of a feature is irrelevant or misleading.
Feature Scaling basically helps to normalize the data within a particular range. Normally several common class
types contain the feature scaling function so that they make feature scaling automatically. However, the SVR class
is not a commonly used class type so we should perform feature scaling using Python.
from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
sc_y = StandardScaler()
X = sc_X.fit_transform(X)
#y = sc_y.fit_transform(y.reshape(len(y),1))
y=y.reshape(-1,1)
y = sc_y.fit_transform(y)
print(X)
print(y)
[[-1.57]
[-1.22]
[-0.87]
[-0.52]
[-0.17]
[ 0.17]
[ 0.52]
[ 0.87]
[ 1.22]
[ 1.57]]
https://colab.research.google.com/drive/1_fY-ZsE19bsvDSsXkKoJmJWkDE19Di8v#scrollTo=ICHe6o5mOxdl&printMode=true 1/3
[[-0.72]
[-0.7 ]
[-0.67]
[-0.6 ]
[-0.49]
[-0.35]
[-0.17]
[ 0.18]
[ 0.88]
[ 2.64]]
Step 4 : Fitting SVR to the dataset
from sklearn.svm import SVR
regressor = SVR(kernel = 'rbf')
regressor.fit(X, y)
/usr/local/lib/python3.8/dist-packages/sklearn/utils/validation.py:993: DataConversionWarning: A column-vector y was passed when a

y = column_or_1d(y, warn=True)
SVR()
Step 5 : Predicting the new Result
y_pred = regressor.predict(sc_X.fit_transform([[6.5]])).reshape(-1,1)
print(y_pred)
[[-0.42]]
# Taking the inverse of the scaled value
y_pred=sc_y.fit_transform(y_pred)
print(y_pred)
[[0.]]
Step 6 : Visualizing the SVR results ( for higher resolution and smoother curve)
# inverse the transformation to go back to the initial scale
plt.scatter(sc_X.inverse_transform(X), sc_y.inverse_transform(y), color = 'red')
plt.plot(sc_X.inverse_transform(X), sc_y.inverse_transform(regressor.predict(X).reshape(-1,1)), color = 'blue')
# add the title to the plot
plt.title('Support Vector Regression Model')
# label x axis
plt.xlabel('Position')
# label y axis
plt.ylabel('Salary Level')
# print the plot
plt.show()
Msc.IT Part 2 Sem 3
Practical 4 : Implementation of Naïve Bayes Classifier.
Importing the libraries
import numpy as np
import pandas as pd
dataset = pd.read_csv('/content/sample_data/Social_Network_Ads.csv')
Splitting the dataset into the Training set and Test set
print(X_train)
https://colab.research.google.com/drive/1_fY-ZsE19bsvDSsXkKoJmJWkDE19Di8v#scrollTo=7EX9Ff4POW4H&printMode=true 1/6
[ 25 80000]
[ 28 85000]
[ 55 39000]
[ 50 88000]
[ 49 88000]
[ 52 150000]
[ 35 65000]
[ 42 54000]
[ 34 43000]
[ 37 52000]
[ 48 30000]
[ 29 43000]
[ 36 52000]
[ 27 54000]
[ 26 118000]]
print(y_train)
[0 1 0 1 1 1 0 0 0 0 0 0 1 1 1 0 1 0 0 1 0 1 0 1 0 0 1 1 1 1 0 1 0 1 0 0 1
0 0 1 0 0 0 0 0 1 1 1 1 0 0 0 1 0 1 0 1 0 0 1 0 0 0 1 0 0 0 1 1 0 0 1 0 1
1 1 0 0 1 1 0 0 1 1 0 1 0 0 1 1 0 1 1 1 0 0 0 0 0 1 0 0 1 1 1 1 1 0 1 1 0
1 0 0 0 0 0 0 0 1 1 0 0 1 0 0 1 0 0 0 1 0 1 1 0 1 0 0 0 0 1 0 0 0 1 1 0 0
0 0 1 0 1 0 0 0 1 0 0 0 0 1 1 1 0 0 0 0 0 0 1 1 1 1 1 0 1 0 0 0 0 0 1 0 0
0 0 0 0 1 1 0 1 0 1 0 0 1 0 0 0 1 0 0 0 0 0 1 0 0 0 0 0 1 0 1 1 0 0 0 0 0
0 1 1 0 0 0 0 1 0 0 0 0 1 0 1 0 1 0 0 0 1 0 0 0 1 0 1 0 0 0 0 0 1 1 0 0 0
0 0 1 0 1 1 0 0 0 0 0 1 0 1 0 0 1 0 0 1 0 1 0 0 0 0 0 0 1 1 1 1 0 0 0 0 1
0 0 0 0]
print(X_test)
[ 41 52000]
[ 27 84000]
[ 35 20000]
[ 43 112000]
[ 27 58000]
[ 37 80000]
[ 52 90000]
[ 26 30000]
[ 49 86000]
[ 57 122000]
[ 34 25000]
[ 35 57000]
[ 34 115000]
[ 59 88000]
[ 45 32000]
[ 29 83000]
[ 26 80000]
[ 49 28000]
[ 23 20000]
[ 32 18000]
[ 60 42000]
[ 19 76000]
[ 36 99000]
[ 19 26000]
[ 60 83000]
[ 24 89000]
[ 27 58000]
[ 40 47000]
[ 42 70000]
[ 32 150000]
[ 35 77000]
[ 22 63000]
[ 45 22000]
[ 27 89000]
[ 18 82000]
[ 42 79000]
[ 40 60000]
[ 53 34000]
[ 47 107000]
[ 58 144000]
[ 59 83000]
[ 24 55000]
[ 26 35000]
[ 58 38000]
[ 42 80000]
[ 40 75000]
[ 59 130000]
[ 46 41000]
[ 41 60000]
[ 42 64000]
[ 37 146000]
[ 23 48000]
[ 25 33000]
[ 24 84000]
[ 27 96000]
[ 23 63000]
[ 48 33000]
[ 48 90000]
[ 42 104000]]
print(y_test)
[0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 1 0 0 1 0 1 0 1 0 0 0 0 0 1 1 0 0 0 0
0 0 1 0 0 0 0 1 0 0 1 0 1 1 0 0 0 1 1 0 0 1 0 0 1 0 1 0 1 0 0 0 0 1 0 0 1
0 0 0 0 1 1 1 0 0 0 1 1 0 1 1 0 0 1 0 0 0 1 0 1 1 1]
Feature Scaling
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
print(X_train)
[ 0.09 1.06]
[-0.11 -0.36]
[-1.2 0.07]
[-0.31 -1.35]
[ 1.57 1.11]
[-0.8 -1.52]
[ 0.09 1.87]
[-0.9 -0.77]
[-0.51 -0.77]
[-0.31 -0.92]
[ 0.28 -0.71]
[ 0.28 0.07]
[ 0.09 1.87]
[-1.1 1.95]
[-1.7 -1.55]
[-1.2 -1.09]
[-0.71 -0.1 ]
[ 0.09 0.1 ]
[ 0.28 0.27]
[ 0.88 -0.57]
[ 0.28 -1.15]
[-0.11 0.68]
[ 2.17 -0.68]
[-1.3 -1.38]
[-1. -0.94]
[-0.01 -0.42]
[-0.21 -0.45]
[-1.8 -0.97]
[ 1.77 1. ]
[ 0.19 -0.36]
[ 0.38 1.11]
[-1.8 -1.35]
[ 0.19 -0.13]
[ 0.88 -1.44]
[-1.99 0.48]
[-0.31 0.27]
[ 1.87 -1.06]
[-0.41 0.07]
[ 1.08 -0.89]
[-1.1 -1.12]
[-1.89 0.01]
[ 0.09 0.27]
[-1.2 0.33]
[-1.3 0.3 ]
[-1. 0.45]
[ 1.67 -0.89]
[ 1.18 0.53]
[ 1.08 0.53]
[ 1.37 2.33]
[-0.31 -0.13]
[ 0.38 -0.45]
[-0.41 -0.77]
[-0.11 -0.51]
[ 0.98 -1.15]
[-0.9 -0.77]
[-0.21 -0.51]
[-1.1 -0.45]
[-1.2 1.4 ]]
print(X_test)
[ 1.87 1.52]
[-0.41 -1.29]
[-0.31 -0.36]
[-0.41 1.32]
[ 2.07 0.53]
[ 0.68 -1.09]
[-0.9 0.39]
[-1.2 0.3 ]
[ 1.08 -1.21]
[-1.5 -1.44]
[-0.61 -1.5 ]
[ 2.17 -0.8 ]
[-1.89 0.19]
[-0.21 0.85]
[-1.89 -1.26]
[ 2.17 0.39]
[-1.4 0.56]
[-1.1 -0.34]
[ 0.19 -0.65]
[ 0.38 0.01]
[-0.61 2.33]
[-0.31 0.22]
[-1.6 -0.19]
[ 0.68 -1.38]
[-1.1 0.56]
[-1.99 0.36]
[ 0.38 0.27]
[ 0.19 -0.28]
[ 1.47 -1.03]
[ 0.88 1.08]
[ 1.97 2.16]
[ 2.07 0.39]
[-1.4 -0.42]
[-1.2 -1. ]
[ 1.97 -0.92]
[ 0.38 0.3 ]
[ 0.19 0.16]
[ 2.07 1.75]
[ 0.78 -0.83]
[ 0.28 -0.28]
[ 0.38 -0.16]
[-0.11 2.22]
[-1.5 -0.63]
[-1.3 -1.06]
[-1.4 0.42]
[-1.1 0.77]
[-1.5 -0.19]
[ 0.98 -1.06]
[ 0.98 0.59]
[ 0.38 1. ]]
Training the Naive Bayes model on the Training set
from sklearn.naive_bayes import GaussianNB
classifier = GaussianNB()
classifier.fit(X_train, y_train)
GaussianNB()
Predicting a new result
print(sc.transform([[30,87000]]))
print(classifier.predict(sc.transform([[40,200000]])))
[[-0.8 0.5]]
[1]
Predicting the Test set results
y_pred = classifier.predict(X_test)
[1 1]
[0 0]
[0 0]
[1 0]
[1 1]
[0 1]
[0 0]
[0 0]
[1 1]
[0 0]
[0 0]
[1 1]
[0 0]
[0 1]
[0 0]
[1 1]
[0 0]
[0 0]
[0 0]
[0 0]
[1 1]
[0 0]
[0 0]
[0 1]
[0 0]
[0 0]
[0 0]
[0 0]
[1 1]
[1 1]
[1 1]
[1 0]
[0 0]
[0 0]
[1 1]
[0 1]
[0 0]
[1 1]
[0 1]
[0 0]
[0 0]
[1 1]
[0 0]
[0 0]
[0 0]
[0 1]
[0 0]
[1 1]
[1 1]
[1 1]]
Making the Confusion Matrix
from sklearn.metrics import confusion_matrix, accuracy_score
cm = confusion_matrix(y_test, y_pred)
print(cm)
accuracy_score(y_test, y_pred)
[[65 3]
[ 7 25]]
0.9
Visualising the Training set results
from matplotlib.colors import ListedColormap
X_set, y_set = sc.inverse_transform(X_train), y_train
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 10, stop = X_set[:, 0].max() + 10, step = 0.25),
np.arange(start = X_set[:, 1].min() - 1000, stop = X_set[:, 1].max() + 1000, step = 0.25))
plt.contourf(X1, X2, classifier.predict(sc.transform(np.array([X1.ravel(), X2.ravel()]).T)).reshape(X1.shape),
alpha = 0.75, cmap = ListedColormap(('red', 'green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1], c = ListedColormap(('red', 'green'))(i), label = j)
plt.title('Naive Bayes (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()
WARNING:matplotlib.axes._axes:*c* argument looks like a single numeric RGB or RGBA sequence, which shou
Visualising the Test set results
X_set, y_set = sc.inverse_transform(X_test), y_test
plt.title('Naive Bayes (Test set)')
plt.xlabel('Age')
plt.legend()
plt.show()
Msc.IT Part 2 Sem 3
Practical 5 : Implementation of Decision Tree Classifier.
Importing the libraries
import numpy as np
import pandas as pd
dataset = pd.read_csv('/content/sample_data/Social_Network_Ads (1).csv')
Splitting the dataset into the Training set and Test set
print(X_train)
[ 25 80000]
[ 28 85000]
[ 55 39000]
[ 50 88000]
[ 49 88000]
[ 52 150000]
[ 35 65000]
[ 42 54000]
[ 34 43000]
[ 37 52000]
[ 48 30000]
[ 29 43000]
[ 36 52000]
[ 27 54000]
[ 26 118000]]
print(y_train)
[0 1 0 1 1 1 0 0 0 0 0 0 1 1 1 0 1 0 0 1 0 1 0 1 0 0 1 1 1 1 0 1 0 1 0 0 1
0 0 1 0 0 0 0 0 1 1 1 1 0 0 0 1 0 1 0 1 0 0 1 0 0 0 1 0 0 0 1 1 0 0 1 0 1
1 1 0 0 1 1 0 0 1 1 0 1 0 0 1 1 0 1 1 1 0 0 0 0 0 1 0 0 1 1 1 1 1 0 1 1 0
1 0 0 0 0 0 0 0 1 1 0 0 1 0 0 1 0 0 0 1 0 1 1 0 1 0 0 0 0 1 0 0 0 1 1 0 0
0 0 1 0 1 0 0 0 1 0 0 0 0 1 1 1 0 0 0 0 0 0 1 1 1 1 1 0 1 0 0 0 0 0 1 0 0
0 0 0 0 1 1 0 1 0 1 0 0 1 0 0 0 1 0 0 0 0 0 1 0 0 0 0 0 1 0 1 1 0 0 0 0 0
0 1 1 0 0 0 0 1 0 0 0 0 1 0 1 0 1 0 0 0 1 0 0 0 1 0 1 0 0 0 0 0 1 1 0 0 0
0 0 1 0 1 1 0 0 0 0 0 1 0 1 0 0 1 0 0 1 0 1 0 0 0 0 0 0 1 1 1 1 0 0 0 0 1
0 0 0 0]
print(X_test)
[ 41 52000]
[ 27 84000]
[ 35 20000]
[ 43 112000]
[ 27 58000]
[ 37 80000]
[ 52 90000]
[ 26 30000]
[ 49 86000]
[ 57 122000]
[ 34 25000]
[ 35 57000]
[ 34 115000]
[ 59 88000]
[ 45 32000]
[ 29 83000]
[ 26 80000]
[ 49 28000]
[ 23 20000]
[ 32 18000]
[ 60 42000]
[ 19 76000]
[ 36 99000]
[ 19 26000]
[ 60 83000]
[ 24 89000]
[ 27 58000]
[ 40 47000]
[ 42 70000]
[ 32 150000]
[ 35 77000]
[ 22 63000]
[ 45 22000]
[ 27 89000]
[ 18 82000]
[ 42 79000]
[ 40 60000]
[ 53 34000]
[ 47 107000]
[ 58 144000]
[ 59 83000]
[ 24 55000]
[ 26 35000]
[ 58 38000]
[ 42 80000]
[ 40 75000]
[ 59 130000]
[ 46 41000]
[ 41 60000]
[ 42 64000]
[ 37 146000]
[ 23 48000]
[ 25 33000]
[ 24 84000]
[ 27 96000]
[ 23 63000]
[ 48 33000]
[ 48 90000]
[ 42 104000]]
print(y_test)
[0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 1 0 0 1 0 1 0 1 0 0 0 0 0 1 1 0 0 0 0
0 0 1 0 0 0 0 1 0 0 1 0 1 1 0 0 0 1 1 0 0 1 0 0 1 0 1 0 1 0 0 0 0 1 0 0 1
0 0 0 0 1 1 1 0 0 0 1 1 0 1 1 0 0 1 0 0 0 1 0 1 1 1]
Feature Scaling
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
print(X_train)
[ 0.09 1.06]
[-0.11 -0.36]
[-1.2 0.07]
[-0.31 -1.35]
[ 1.57 1.11]
[-0.8 -1.52]
[ 0.09 1.87]
[-0.9 -0.77]
[-0.51 -0.77]
[-0.31 -0.92]
[ 0.28 -0.71]
[ 0.28 0.07]
[ 0.09 1.87]
[-1.1 1.95]
[-1.7 -1.55]
[-1.2 -1.09]
[-0.71 -0.1 ]
[ 0.09 0.1 ]
[ 0.28 0.27]
[ 0.88 -0.57]
[ 0.28 -1.15]
[-0.11 0.68]
[ 2.17 -0.68]
[-1.3 -1.38]
[-1. -0.94]
[-0.01 -0.42]
[-0.21 -0.45]
[-1.8 -0.97]
[ 1.77 1. ]
[ 0.19 -0.36]
[ 0.38 1.11]
[-1.8 -1.35]
[ 0.19 -0.13]
[ 0.88 -1.44]
[-1.99 0.48]
[-0.31 0.27]
[ 1.87 -1.06]
[-0.41 0.07]
[ 1.08 -0.89]
[-1.1 -1.12]
[-1.89 0.01]
[ 0.09 0.27]
[-1.2 0.33]
[-1.3 0.3 ]
[-1. 0.45]
[ 1.67 -0.89]
[ 1.18 0.53]
[ 1.08 0.53]
[ 1.37 2.33]
[-0.31 -0.13]
[ 0.38 -0.45]
[-0.41 -0.77]
[-0.11 -0.51]
[ 0.98 -1.15]
[-0.9 -0.77]
[-0.21 -0.51]
[-1.1 -0.45]
[-1.2 1.4 ]]
print(X_test)
[ 1.87 1.52]
[-0.41 -1.29]
[-0.31 -0.36]
[-0.41 1.32]
[ 2.07 0.53]
[ 0.68 -1.09]
[-0.9 0.39]
[-1.2 0.3 ]
[ 1.08 -1.21]
[-1.5 -1.44]
[-0.61 -1.5 ]
[ 2.17 -0.8 ]
[-1.89 0.19]
[-0.21 0.85]
[-1.89 -1.26]
[ 2.17 0.39]
[-1.4 0.56]
[-1.1 -0.34]
[ 0.19 -0.65]
[ 0.38 0.01]
[-0.61 2.33]
[-0.31 0.22]
[-1.6 -0.19]
[ 0.68 -1.38]
[-1.1 0.56]
[-1.99 0.36]
[ 0.38 0.27]
[ 0.19 -0.28]
[ 1.47 -1.03]
[ 0.88 1.08]
[ 1.97 2.16]
[ 2.07 0.39]
[-1.4 -0.42]
[-1.2 -1. ]
[ 1.97 -0.92]
[ 0.38 0.3 ]
[ 0.19 0.16]
[ 2.07 1.75]
[ 0.78 -0.83]
[ 0.28 -0.28]
[ 0.38 -0.16]
[-0.11 2.22]
[-1.5 -0.63]
[-1.3 -1.06]
[-1.4 0.42]
[-1.1 0.77]
[-1.5 -0.19]
[ 0.98 -1.06]
[ 0.98 0.59]
[ 0.38 1. ]]
Training the Decision Tree model on the Training set
from sklearn.tree import DecisionTreeClassifier
classifier = DecisionTreeClassifier()
classifier.fit(X_train, y_train)
DecisionTreeClassifier()
Predicting a new result
[0]
[1]
Predicting the Test set results
y_pred = classifier.predict(X_test)
[1 1]
[0 0]
[0 0]
[1 0]
[1 1]
[1 1]
[0 0]
[0 0]
[1 1]
[0 0]
[0 0]
[1 1]
[0 0]
[1 1]
[0 0]
[1 1]
[0 0]
[0 0]
[0 0]
[1 0]
[1 1]
[0 0]
[0 0]
[1 1]
[0 0]
[0 0]
[0 0]
[0 0]
[1 1]
[1 1]
[1 1]
[1 0]
[0 0]
[0 0]
[1 1]
[0 1]
[0 0]
[1 1]
[1 1]
[0 0]
[0 0]
[1 1]
[0 0]
[0 0]
[0 0]
[1 1]
[0 0]
[1 1]
[1 1]
[1 1]]
Making the Confusion Matrix
from sklearn.metrics import confusion_matrix, accuracy_score
cm = confusion_matrix(y_test, y_pred)
print(cm)
accuracy_score(y_test, y_pred)
[[62 6]
[ 4 28]]
0.9
Visualising the Training set results
X_set, y_set = sc.inverse_transform(X_train), y_train
plt.title('Naive Bayes (Training set)')
plt.xlabel('Age')
plt.legend()
plt.show()
Visualising the Test set results
X_set, y_set = sc.inverse_transform(X_test), y_test
plt.title('Naive Bayes (Test set)')
plt.xlabel('Age')
plt.legend()
plt.show()
Siddhant Mandal
Siddhant Mandal

Ilovepdf Merged

Uploaded by

Copyright:

Available Formats

Ilovepdf Merged

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Ilovepdf Merged

Uploaded by

Copyright:

Available Formats

Name : ____Siddhant Mandal________ Subject: Machine Learning

Class: MSC-II (Artificial intelligence) Exam Seat no: _3269587_____

Academic Year: 2022-2023

No Date TITLE Page SIGN

9 Implementation of hierarchical clustering

Executed by Siddhant Mandal

University Department of Information Technology

D.G. Ruparel College

Msc.IT Part 2 Sem 3

Subject = Machine Learning

Practical 1 : Implementation of Simple Linear Regression

Importing the Libraries

Importing the dataset

[ 39343. 46205. 37731. 43525. 39891. 56642. 60150. 54445. 64445.

[ 56642. 66029. 64445. 61111. 113812. 91738. 46205. 121872. 60150.

[ 37731. 122391. 57081. 63218. 116969. 109431. 112635. 55794. 83088.

Training the Simple Linear Regression Model on the Training Set

Predicting the Test Set Result

Visualizing the Training Set Results

Visualizing the Test Set Results

Colab paid products - Cancel contracts here

check 0s completed at 2:20 AM

Executed by Siddhant Mandal

University Department of Information Technology

D.G. Ruparel College

Msc.IT Part 2 Sem 3

Subject = Machine Learning

Practical 2 : Implementation of Multiple Linear Regression.

Importing the Libraries

Importing the dataset

[[165349.2 136897.8 471784.1 'New York']

[192261.83 191792.06 191050.39 182901.99 166187.94 156991.12 156122.51

Encoding Categorical Data

[[0.0 0.0 1.0 165349.2 136897.8 471784.1]

Training the Multiple Linear Regression Model on the Training Set

Predicting the Test Set Results

Colab paid products - Cancel contracts here

Executed by Siddhant Mandal

University Department of Information Technology

D.G. Ruparel College

Msc.IT Part 2 Sem 3

Subject = Machine Learning

Practical 3 : Implementation of Support Vector Regression.

Step 1 :Importing the Libraries

step 2: Reading the dataset

Step 3: Feature Scaling

Step 4 : Fitting SVR to the dataset

/usr/local/lib/python3.8/dist-packages/sklearn/utils/validation.py:993: DataConversionWarning: A column-vector y was passed when a

Step 5 : Predicting the new Result

check 0s completed at 2:50 AM

Executed by Siddhant Mandal

University Department of Information Technology

D.G. Ruparel College

Msc.IT Part 2 Sem 3

Subject = Machine Learning

Practical 4 : Implementation of Naïve Bayes Classifier.

Importing the libraries

Importing the dataset

Training the Naive Bayes model on the Training set

Predicting a new result

Name : Siddhant Mandal____ Subject: Machine Learning

check 0s completed at 2:20 AM

check 0s completed at 2:50 AM

check 31s completed at 3:09 AM

check 34s completed at 3:19 AM