Machine Learning Hands-On

KLE Technological University Page |1
MACHINE LEARNING HANDS-ON PROGRAMS
Program 1: Linear Regression – Single Variable Linear Regression
Description About Dataset :

Performing the Linear regression for Single variable by using Salary_Data.csv which is consists of two
features that is Salary, YearsExperience.Each column contains 30 rows of information. Feature “Salary”
describes Each person salary according to his/her year of experience.
//Python code to perform Single variable linear regression

from google.colab import drive
drive.mount('/content/drive')
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
"""**Importing the dataset**"""
dataset=pd.read_csv('/content/drive/My Drive/Machine Learning/Chapter1/Salary_Data.csv')

X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, -1].values
print(y)
print(X)
"""**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)
"""**Training the Simple Linear Regression model on the Training set**"""
from sklearn.linear_model import LinearRegression

regressor = LinearRegression()
regressor.fit(X_train, y_train)
y_pred = regressor.predict(X_test)
print(y_pred)
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)')
USN: 01FE21MCA023
plt.xlabel('Years of Experience')
plt.ylabel('Salary')
plt.show()
"""**Visualising the Test set results**"""
plt.scatter(X_test, y_test, color = 'red')

plt.plot(X_train, regressor.predict(X_train), color = 'blue')
plt.title('Salary vs Experience (Test set)')
plt.xlabel('Years of Experience')
plt.ylabel('Salary')
plt.show()
USN: 01FE21MCA023
Program 2: Linear Regression – Multi Variable Linear Regression
Description About Dataset:

Performing the linear regression using multi linear regression on 50_Startups.csv which is consist of 5
features that is R&D, Marketing, Spend, Administration, Spend, State, Profit. Each column contains 50
rows of information.
//Python code to perform Multi variable linear regression

# Importing the libraries
import numpy as np
import pandas as pd
# Importing the dataset
dataset = pd.read_csv('/content/drive/My Drive/Machine Learning/Chapter1/MachineLearning-
master/Multiple Linear Regression Code Dataset-20230331.zip (Unzipped Files)/50_Startups.csv')
# 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)
#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)
# 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))
USN: 01FE21MCA023
Program 3: Classification – Logistic Regression

Performing the Logistic Regression on Social_Network_Ads. csv which is consists of three features that is
Age, EstimatedSalary, purchased. Each column contains 400 rows of information. Feature “Age” describes
Each person age and according to his/ Estimated Salary . depending on which he/she will decide to purchase
a particular item or not.
//Python code to perform Classification – Logistic Regression

import numpy as np
import pandas as pd
master/Social_Network_Ads.csv')
# Splitting the dataset into the Training set and Test set
print(X_train)
print(y_train)
print(X_test)
print(y_test)
# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
print(X_train)
print(X_test)
# Training the Logistic Regression model on the Training set
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression(random_state=0)
classifier.fit(X_train, y_train)
#Predict the result for Age = 30 and EstimatedSalary = 87000

print(classifier.predict(sc.transform([[30, 87000]])))
#Predicting the Test Set results

y_pred = classifier.predict(X_test)
print(y_pred)
print(np.concatenate((y_pred.reshape(len(y_pred),1),
y_test.reshape(len(y_test),1)),1))
# Making the Confusion Matrix
USN: 01FE21MCA023
from sklearn.metrics import confusion_matrix, accuracy_score

cm = confusion_matrix(y_test, y_pred)
print(cm)
accuracy_score(y_test, y_pred)
# 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('Logistic Regression (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()
# Visualising the Test set results

X_set, y_set = sc.inverse_transform(X_test), y_test
0.25),
USN: 01FE21MCA023

plt.title('Logistic Regression (Test set)')
plt.xlabel('Age')
plt.legend()
plt.show()
USN: 01FE21MCA023
Program 4: Classification – Support Vector Machines (SVM)

Performing the Support Vector Machines on Social_Network_Ads. csv which is consists of three features
that is Age, EstimatedSalary, purchased. Each column contains 400 rows of information. Feature “Age”
describes Each person age and according to his/ Estimated Salary . depending on which he/she will decide
to purchase a particular item or not.
//Python code to perform Classification – Support Vector Machines (SVM)

# Support Vector Machine (SVM)
# Importing the libraries
import numpy as np
import pandas as pd
master/Social_Network_Ads.csv')
# Splitting the dataset into the Training set and Test set
print(X_train)
print(y_train)
print(X_test)
print(y_test)
# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
print(X_train)
print(X_test)
# Training the SVM model on the Training set
from sklearn.svm import SVC
classifier = SVC(kernel = 'linear', random_state = 0)
# Predicting a new result
print(classifier.predict(sc.transform([[30,87000]])))
USN: 01FE21MCA023
# 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)
0.25),
plt.title('SVM (Training set)')
plt.xlabel('Age')
plt.legend()
plt.show()

0.25),
USN: 01FE21MCA023

plt.title('SVM (Test set)')
plt.xlabel('Age')
plt.legend()
plt.show()
# Training the SVM model on the Training set

from sklearn.svm import SVC
classifier = SVC(kernel = 'rbf', random_state = 0)


0.25),
USN: 01FE21MCA023
KLE Technological University P a g e | 10
plt.title('SVM (Training set)')
plt.xlabel('Age')
plt.legend()
plt.show()

0.25),
plt.title('SVM (Test set)')
plt.xlabel('Age')
plt.legend()
plt.show()
USN: 01FE21MCA023
USN: 01FE21MCA023
Program 5: Classification using Neural Networks

Performing the Classification using Neural Networks on pima-indians-diabetes.csv which is consists of
nine features that is X1,X2,X3,X4,X5,X6,X7,X8,X9 . Each column contains 767 rows of information.
//Python code to perform Classification using Neural Networks
# first neural network with keras tutorial
from numpy import loadtxt
from keras.models import Sequential
from keras.layers import Dense
# load the dataset
dataset = loadtxt('/content/drive/My Drive/pima-indians-diabetes.csv', delimiter=',')
# split into input (X) and output (y) variables
X = dataset[:,0:8]
y = dataset[:,8]
dataset.shape
(768, 9)
X.shape
(768, 8)
y.shape
(768,)
# define the keras model
model = Sequential() #calling default constructor
#First Hidden Layer (along with input layer)
model.add(Dense(12, input_dim=8, activation='relu')) #adding input layer along with the 1st hidden layer
#1st hidden layer has 12 activation units, input layer has 8 units for 8 features
#activation function used in the 1st layer is ReLU
#Adding the 2nd Hidden layer with 8 activation nodes and ReLU function
model.add(Dense(12, activation='relu'))
#Adding output layer with 1 activation unit (binary classification) and with Sigmoid function
model.add(Dense(1, activation='sigmoid'))
# compile the keras model
#Loss means computing the error or cost function (using algorithm - binary_crossentropy)
#Algorithm used is 'adam' - Stochastic gradient descent algorithm
#Evaluating the performance of the model will be done using 'accuracy'
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
# fit the keras model on the dataset
# Batch size is for updating the weights. Weights are updated after every 10 rows are executed.
model.fit(X, y, epochs=200, batch_size=40)
Epoch 1/200
77/77 [==============================] - 0s 1ms/step - loss: 0.5050 - accuracy: 0.7591
Epoch 2/200
77/77 [==============================] - 0s 963us/step - loss: 0.5148 - accuracy: 0.7435
Epoch 3/200
USN: 01FE21MCA023
Epoch 4/200
Epoch 5/200
Epoch 6/200
Epoch 7/200
Epoch 8/200
Epoch 9/200
Epoch 10/200
Epoch 11/200
Epoch 12/200
Epoch 13/200
...
Epoch 199/200
Epoch 200/200
Accuracy: 76.56
# make probability predictions with the model
predictions = model.predict(X)
# round predictions
rounded = [round(x[0]) for x in predictions]
# make class predictions with the model
predictions = model.predict_classes(X)
# make class predictions with the model
predictions = model.predict_classes(X)
# summarize the first 5 cases
for i in range(5):
print('%s => %d (expected %d)' % (X[i].tolist(), predictions[i], y[i]))
[6.0, 148.0, 72.0, 35.0, 0.0, 33.6, 0.627, 50.0] => 0 (expected 1)
[1.0, 85.0, 66.0, 29.0, 0.0, 26.6, 0.351, 31.0] => 0 (expected 0)
[8.0, 183.0, 64.0, 0.0, 0.0, 23.3, 0.672, 32.0] => 1 (expected 1)
[1.0, 89.0, 66.0, 23.0, 94.0, 28.1, 0.167, 21.0] => 0 (expected 0)
[0.0, 137.0, 40.0, 35.0, 168.0, 43.1, 2.288, 33.0] => 1 (expected 1)
USN: 01FE21MCA023
Program 6: Unsupervised Learning – K-Means Clustering

Performing the K-Means Clustering which is the technique of unsupervised learning by using
Mall_Customers.csv which is consists of four e features that is CustomerID, Genre, Age, Annual Income,
Spending Score (1-100). Each column contains 200 rows of information. Features used to describes whether
person will purchase a particular item or not based on persons age, genre and Annual Income.
//Python code to perform Unsupervised Learning – K-Means Clustering
import numpy as np
import pandas as pd
master/Mall_Customers.csv')
X = dataset.iloc[:, [3, 4]].values
# y = dataset.iloc[:, 3].values
# Using the elbow method to find the optimal number of clusters
from sklearn.cluster import KMeans
wcss = []
for i in range(1, 11):
kmeans = KMeans(n_clusters = i, init = 'k-means++', max_iter = 300, n_init = 10, random_state = 42)
kmeans.fit(X)
wcss.append(kmeans.inertia_)
plt.plot(range(1, 11), wcss)
plt.title('The Elbow Method')
plt.xlabel('Number of clusters')
plt.ylabel('WCSS')
plt.show()
# Fitting K-Means to the dataset

kmeans = KMeans(n_clusters = 5, init = 'k-means++', max_iter = 300, n_init = 10, random_state = 42)
y_kmeans = kmeans.fit_predict(X)
USN: 01FE21MCA023
# Visualising the clusters

plt.scatter(X[y_kmeans == 0, 0], X[y_kmeans == 0, 1], s = 100, c = 'red', label = 'Cluster 1')
plt.scatter(X[y_kmeans == 1, 0], X[y_kmeans == 1, 1], s = 100, c = 'blue', label = 'Cluster 2')
plt.scatter(X[y_kmeans == 2, 0], X[y_kmeans == 2, 1], s = 100, c = 'green', label = 'Cluster 3')
plt.scatter(X[y_kmeans == 3, 0], X[y_kmeans == 3, 1], s = 100, c = 'cyan', label = 'Cluster 4')
plt.scatter(X[y_kmeans == 4, 0], X[y_kmeans == 4, 1], s = 100, c = 'magenta', label = 'Cluster 5')
plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], s = 300, c = 'yellow', label =
'Centroids')
plt.title('Clusters of customers')
plt.xlabel('Annual Income (k$)')
plt.ylabel('Spending Score (1-100)')
plt.legend()
plt.show()
USN: 01FE21MCA023
Program 7: Convolution Neural Networks Application

Performing the Convolution Neural Networks Application on image dataset to predict between black-
diamond watermelon and caroline watermelon. Training_set contain the images of both the types of
watermelons. One folder containing image dataset of both the watermelons which is divided as test and
training dataset. Training_set folder contains black-diamond watermelon (500) images and caroline
watermelon (500) images and Test image dataset contains black-diamond watermelon (100), caroline
watermelon (100) images.
//Python code to perform Convolution Neural Networks Application

import tensorflow as tf
from keras.preprocessing.image import ImageDataGenerator
## Part 1 - Data Preprocessing

### Preprocessing the Training set
train_datagen = ImageDataGenerator(rescale = 1./255,
shear_range = 0.2,
zoom_range = 0.2,
horizontal_flip = True)
training_set = train_datagen.flow_from_directory('/content/drive/My Drive/training_set',
target_size = (64, 64),
batch_size = 64,
class_mode = 'binary')
### Preprocessing the Test set

test_datagen = ImageDataGenerator(rescale = 1./255)
test_set = test_datagen.flow_from_directory('/content/drive/My Drive/test_set',
target_size = (64, 64),
batch_size = 64,
class_mode = 'binary')
## Part 2 - Building the CNN

### Initialising the CNN
cnn = tf.keras.models.Sequential()
### Step 1 - Convolution
cnn.add(tf.keras.layers.Conv2D(filters=32, kernel_size=3, activation='relu', input_shape=[64, 64, 3]))
### Step 2 - Pooling
cnn.add(tf.keras.layers.MaxPool2D(pool_size=2, strides=2))
### Adding a second convolutional layer
cnn.add(tf.keras.layers.Conv2D(filters=32, kernel_size=3, activation='relu'))
cnn.add(tf.keras.layers.MaxPool2D(pool_size=2, strides=2))
USN: 01FE21MCA023
### Step 3 - Flattening

cnn.add(tf.keras.layers.Flatten())
### Step 4 - Full Connection
cnn.add(tf.keras.layers.Dense(units=128, activation='relu'))
### Step 5 - Output Layer
cnn.add(tf.keras.layers.Dense(units=1, activation='sigmoid'))
## Part 3 - Training the CNN

### Compiling the CNN
cnn.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])
### Training the CNN on the Training set and evaluating it on the Test set
cnn.fit(x = training_set, validation_data = test_set, epochs = 10)
Epoch 1/10
Epoch 2/10
16/16 [==============================] - 0s 963us/step - loss: 0.5148 - accuracy: 0.7435
Epoch 3/10
Epoch 4/10
Epoch 5/10
Epoch 6/10
Epoch 7/10
Epoch 8/10
Epoch 9/10
Epoch 10/10
# Saving the model

cnn.save('watermelon.h5')
## Part 4 - Making a single prediction

import numpy as np
from keras.preprocessing import image
import keras.utils as image
test_image = image.load_img('/content/drive/My Drive/600.jpg', target_size = (64, 64))
test_image = image.img_to_array(test_image)
test_image = np.expand_dims(test_image, axis = 0)
result = cnn.predict(test_image)
training_set.class_indices
if result[0][0] == 1:
USN: 01FE21MCA023
prediction = 'caroline watermelon '

else:
prediction = 'black diamon watermelon '
print(prediction)
USN: 01FE21MCA023

Machine Learning Hands-On

Uploaded by

Document Information

Original Description:

Original Title

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

Machine Learning Hands-On

Uploaded by

Copyright:

Available Formats

KLE Technological University Page |1

MACHINE LEARNING HANDS-ON PROGRAMS

Program 1: Linear Regression – Single Variable Linear Regression

Description About Dataset :

//Python code to perform Single variable linear regression

"""**Importing the dataset**"""

dataset=pd.read_csv('/content/drive/My Drive/Machine Learning/Chapter1/Salary_Data.csv')

from sklearn.model_selection import train_test_split

"""**Training the Simple Linear Regression model on the Training set**"""

from sklearn.linear_model import LinearRegression

plt.scatter(X_train, y_train, color = 'red')

"""**Visualising the Test set results**"""

plt.scatter(X_test, y_test, color = 'red')

Program 2: Linear Regression – Multi Variable Linear Regression

Description About Dataset:

//Python code to perform Multi variable linear regression

from sklearn.model_selection import train_test_split

Program 3: Classification – Logistic Regression

Description About Dataset:

//Python code to perform Classification – Logistic Regression

#Predict the result for Age = 30 and EstimatedSalary = 87000

#Predicting the Test Set results

from sklearn.metrics import confusion_matrix, accuracy_score

# Visualising the Test set results

plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1], c = ListedColormap(('red', 'green'))(i), label = j)

Program 4: Classification – Support Vector Machines (SVM)

Description About Dataset:

//Python code to perform Classification – Support Vector Machines (SVM)

# Predicting a new result

# Predicting the Test set results

from matplotlib.colors import ListedColormap

plt.contourf(X1, X2, classifier.predict(sc.transform(np.array([X1.ravel(),

# Training the SVM model on the Training set

# Predicting the Test set results

# Visualising the Training set results

# Visualising the Test set results

Program 5: Classification using Neural Networks

Description About Dataset:

Program 6: Unsupervised Learning – K-Means Clustering

# Fitting K-Means to the dataset

# Visualising the clusters

Program 7: Convolution Neural Networks Application

Description About Dataset:

//Python code to perform Convolution Neural Networks Application

from google.colab import drive

## Part 1 - Data Preprocessing

### Preprocessing the Test set

## Part 2 - Building the CNN

### Step 3 - Flattening

## Part 3 - Training the CNN

# Saving the model

## Part 4 - Making a single prediction

prediction = 'caroline watermelon '

You might also like

"""Importing the dataset"""

"""Training the Simple Linear Regression model on the Training set"""

"""Visualising the Test set results"""