FML_LAB FILE
Practical File
Submitted in partial fulfillment for the evaluation of
“Fundamentals of Machine
Learning-Lab”
Submitted By:
NAME: Kunal Saini, Aditya Jain, Aditi Jain, Ananya Tyagi, Aditya Vikram
ENROLL NO: 07317711621, 07617711621, 08217711621, 08817711621, 09117711621
BRANCH & SECTION: AI & ML-B
Submitted To:
Dr. Sonakshi Vij
1
FML_LAB FILE
INDEX
S.No Details Page Date Grade/Evaluation Sign
No.
1 Study and implement
Linear Regression
2 Study and implement
Logistic Regression
3 Study and implement K
nearest neighbour
(KNN)
4 Study and implement
Classification using
SVM
5 Study and implement
Bagging using Random
Forests
6 Study and implement
Naïve Bayes
7 Study and implement
Decision Trees
8 Study and implement
K-means Clustering to
find Natural Patterns in
data
9 Study and implement
Gaussian Mixture
Model using the
Expectation
Maximization
10 Study and implement
Classification based on
association rules
2
FML_LAB FILE
3
FML_LAB FILE
EXPERIMRNT-1
(LINEAR REGRESSION)
ABSTRACT:
4
FML_LAB FILE
CODE:
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
# Load the dataset
data = pd.read_csv('data.csv')
# Select the 'perimeter_mean' and 'concavity_mean' columns for linear regression
X = data[['perimeter_mean']] # Predictor variable
y = data['concavity_mean'] # Target variable
# Create a linear regression model
model = LinearRegression()
# Fit the model to the data
model.fit(X, y)
# Perform predictions
y_pred = model.predict(X)
# Calculate the mean squared error
mse = mean_squared_error(y, y_pred)
print("Mean Squared Error:", mse)
# Plot the linear regression line
plt.scatter(X, y, color='blue', label='Data')
plt.plot(X, y_pred, color='red', label='Linear Regression')
5
FML_LAB FILE
plt.xlabel('Perimeter_mean')
plt.ylabel('Concavity_mean')
plt.title('Linear Regression')
plt.legend()
plt.show()
OUTPUT:
LEARNING OUTCOMES:
6
FML_LAB FILE
EXPERIMENT-2
(LOGISTIC REGRESSION)
ABSTRACT:
7
FML_LAB FILE
CODE:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, confusion_matrix
from sklearn.model_selection import train_test_split
# Load the dataset
data = pd.read_csv('data.csv')
# Select the 'perimeter_mean' and 'diagnosis' columns for logistic regression
X = data[['perimeter_mean']] # Predictor variable
y = data['diagnosis'] # Target variable
# Reshape feature to a 1-dimensional array
X = np.array(X).reshape(-1, 1)
# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Create a logistic regression model
model = LogisticRegression()
# Fit the model to the training data
model.fit(X_train, y_train)
# Perform predictions on the test data
y_pred = model.predict(X_test)
8
FML_LAB FILE
# Calculate the accuracy of the model
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
# Create a confusion matrix
confusion_mat = confusion_matrix(y_test, y_pred)
print("Confusion Matrix:")
print(confusion_mat)
# Plot the logistic regression curve
X_range = np.linspace(X.min(), X.max(), 100).reshape(-1, 1)
y_proba = model.predict_proba(X_range)[:, 1]
plt.scatter(X, y, color='blue', label='Data')
plt.plot(X_range, y_proba, color='red', label='Logistic Regression')
plt.xlabel('perimeter_mean')
plt.ylabel('diagnosis')
plt.title('Logistic Regression')
plt.legend()
plt.show()
OUTPUT:
LEARNING OUTCOMES:
9
FML_LAB FILE
EXPERIMENT-3
(K NEAREST NEIGHBOR)
ABSTRACT:
10
FML_LAB FILE
CODE:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score, confusion_matrix
# Load the dataset
data = pd.read_csv('data.csv')
# Select the relevant features and target variable
X = data[['radius_mean', 'perimeter_mean', 'concavity_mean', 'smoothness_mean',
'texture_mean']]
y = data['id']
# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Create a KNN classifier with k=5
knn = KNeighborsClassifier(n_neighbors=5)
# Fit the model to the training data
knn.fit(X_train, y_train)
# Perform predictions on the test data
y_pred = knn.predict(X_test)
# Calculate the accuracy of the model
accuracy = accuracy_score(y_test, y_pred)
11
FML_LAB FILE
print("Accuracy:", accuracy)
# Create a confusion matrix
confusion_mat = confusion_matrix(y_test, y_pred)
print("Confusion Matrix:")
print(confusion_mat)
# Scatter plot
plt.scatter(data['radius_mean'], data['concavity_mean'], c=data['id'], cmap='coolwarm')
plt.xlabel('Radius_mean')
plt.ylabel('Concavity_mean')
plt.title('KNN')
plt.colorbar(label='Id')
plt.show()
OUTPUT:
LEARNING OUTCOMES:
12
FML_LAB FILE
EXPERIMENT-4
(CLASSIFICATION USING SVM)
ABSTRACT:
13
FML_LAB FILE
CODE:
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.svm import SVR
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import r2_score
# Load the CSV file into a pandas dataframe
df = pd.read_csv('data.csv')
# Extract the relevant features
X = df[['perimeter_mean']]
y = df['concavity_mean']
# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Scale the data
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)
# Train the SVM model
svm_regressor = SVR(kernel='rbf')
svm_regressor.fit(X_train_scaled, y_train)
# Make predictions on the test data
y_pred = svm_regressor.predict(X_test_scaled)
14
FML_LAB FILE
# Calculate the coefficient of determination (R^2) on the test data
r2 = r2_score(y_test, y_pred)
print('R^2 score:', r2)
# Plot the predicted values and the actual values on the test data
plt.figure(figsize=(10, 5))
plt.scatter(X_test, y_test, color='red')
plt.plot(X_test, y_pred, color='blue', linewidth=3)
plt.xlabel('perimeter_mean')
plt.ylabel('concavity_mean')
plt.title('Support Vector Regression')
plt.show()
OUTPUT:
LEARNING OUTCOMES:
15
FML_LAB FILE
EXPERIMENT-5
(BAGGING USING RANDOM FORESTS)
ABSTRACT:
16
FML_LAB FILE
CODE:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, confusion_matrix
# Load the dataset
data = pd.read_csv('data.csv')
# Select the features and target variable
X=data[['perimeter_mean','area_mean','concavity_mean','radius_mean','texture_mean','smoot
hness_mean']]
#X = X.dropna()
y = data['diagnosis']
# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Create a Random Forest classifier with 100 trees
rf = RandomForestClassifier(n_estimators=100, random_state=42)
# Fit the model to the training data
rf.fit(X_train, y_train)
# Perform predictions on the test data
y_pred = rf.predict(X_test)
# Calculate the accuracy of the model
17
FML_LAB FILE
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
# Create a confusion matrix
confusion_mat = confusion_matrix(y_test, y_pred)
print("Confusion Matrix:")
print(confusion_mat)
# Feature Importance
feature_importance = rf.feature_importances_
feature_names = X.columns
# Sort feature importance in descending order
sorted_indices = np.argsort(feature_importance)[::-1]
sorted_feature_names = feature_names[sorted_indices]
sorted_feature_importance = feature_importance[sorted_indices]
# Bar plot of feature importance
plt.figure(figsize=(10, 6))
sns.barplot(x=sorted_feature_importance, y=sorted_feature_names)
plt.xlabel('Feature Importance')
plt.ylabel('Features')
plt.title('Random Forest')
plt.show()
18
FML_LAB FILE
OUTPUT:
LEARNING OUTCOMES:
19
FML_LAB FILE
EXPERIEMNT-6
(NAIVE BAYES)
ABSTRACT:
20
FML_LAB FILE
CODE:
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import confusion_matrix, classification_report
# Load the dataset
data = pd.read_csv("data.csv")
# Split the dataset into features (X) and target variable (y)
X=data[['perimeter_mean','area_mean','concavity_mean','radius_mean','texture_mean','smoot
hness_mean']]
#X = X.dropna()
y = data['diagnosis']
# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Create a Gaussian Naive Bayes model
naive_bayes = GaussianNB()
# Train the model
naive_bayes.fit(X_train, y_train)
# Make predictions on the test set
y_pred = naive_bayes.predict(X_test)
# Create a confusion matrix
21
FML_LAB FILE
cm = confusion_matrix(y_test, y_pred)
# Plot the confusion matrix plt.figure(figsize=(8, 6))
sns.heatmap(cm, annot=True, cmap="Blues", fmt="d",
cbar=False) plt.title("Confusion Matrix")
plt.xlabel("Predicted")
plt.ylabel("Actual")
plt.show()
# Create a classification report
report = classification_report(y_test, y_pred)
# Print the classification report
print("Classification Report:")
print(report)
OUTPUT:
LEARNING OUTCOMES:
22
FML_LAB FILE
EXPERIMENT-7
(DECISION TREES)
ABSTRACT:
23
FML_LAB FILE
CODE:
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.metrics import classification_report
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier, plot_tree
from sklearn.metrics import confusion_matrix
# Load the dataset
data = pd.read_csv("data.csv")
# Split the dataset into features (X) and target variable (y)
X=data[['perimeter_mean','area_mean','concavity_mean','radius_mean','texture_mean','smoot
hness_mean']]
#X = X.dropna()
y = data['diagnosis']
# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Create a Decision Tree classifier
decision_tree = DecisionTreeClassifier()
# Train the model
decision_tree.fit(X_train, y_train)
# Plot the decision tree
plt.figure(figsize=(12, 8))
plot_tree(decision_tree, feature_names=X.columns, class_names=['0','1'], filled=True)
24
FML_LAB FILE
plt.title("Decision Tree")
plt.show()
# Make predictions on the test set
y_pred = decision_tree.predict(X_test)
# Create a confusion matrix
cm = confusion_matrix(y_test, y_pred)
# Plot the confusion matrix
plt.figure(figsize=(8, 6))
sns.heatmap(cm, annot=True, cmap="Blues", fmt="d",
cbar=False) plt.title("Confusion Matrix")
plt.xlabel("Predicted")
plt.ylabel("Actual")
plt.show()
# Generate the classification report
report = classification_report(y_test, y_pred)
print("Classification Report:")
print(report)
25
FML_LAB FILE
OUTPUT:
LEARNING OUTCOMES:
26
FML_LAB FILE
EXPERIMENT-8
(K MEANS CLUSTERING)
ABSTRACT:
27
FML_LAB FILE
CODE:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
# Load the dataset
data = pd.read_csv('data.csv')
# Extract the features
X = data[['concavity_mean', 'perimeter_mean']].values
# Number of clusters (k)
k=3
# Create a KMeans instance
kmeans = KMeans(n_clusters=k)
# Fit the model to the data
kmeans.fit(X)
# Obtain the cluster labels for the data
labels = kmeans.labels_
# Obtain the cluster centers
centers = kmeans.cluster_centers_
# Print the cluster labels and centers
print("Cluster Labels:")
28
FML_LAB FILE
print(labels)
print("Cluster Centers:")
print(centers)
# Scatter plot of the data points with cluster assignments and centers
plt.scatter(X[:, 0], X[:, 1], c=labels, cmap='viridis')
plt.scatter(centers[:, 0], centers[:, 1], marker='X', color='red', label='Centers')
plt.xlabel('Concavity_mean')
plt.ylabel('Perimeter_mean')
plt.title('K-means Clustering')
plt.legend()
plt.show()
OUTPUT:
LEARNING OUTCOMES:
29
FML_LAB FILE
EXPERIMENT-9
(GAUSSIAN MIXTURE MODEL)
ABSTRACT:
30
FML_LAB FILE
CODE:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.mixture import GaussianMixture
# Load the dataset
data = pd.read_csv('data.csv')
# Extract the features
X = data[['concavity_mean', 'area_mean']].values
# Number of clusters/components (k)
k=3
# Create a Gaussian Mixture Model instance
gmm = GaussianMixture(n_components=k)
# Fit the model to the data
gmm.fit(X)
# Obtain the predicted labels for the data
labels = gmm.predict(X)
# Get the probabilities of each data point belonging to each cluster
probs = gmm.predict_proba(X)
# Print the cluster labels and probabilities
print("Cluster Labels:")
31
FML_LAB FILE
print(labels)
print("Probabilities:")
print(probs)
# Scatter plot of the data points with cluster assignments
plt.scatter(X[:, 0], X[:, 1], c=labels, cmap='viridis')
plt.xlabel('Concavity_mean')
plt.ylabel('Area_mean')
plt.title('Gaussian Mixture Model Clustering')
plt.show()
OUTPUT:
LEARNING OUTCOMES:
32
FML_LAB FILE
EXPERIMENT-10
(CLASSIFICATION BASED ON ASSOCIATION RULES)
ABSTRACT:
33
FML_LAB FILE
CODE:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, confusion_matrix
# Load the dataset
data = pd.read_csv('data.csv')
# Select the features and target variable
X = data[['radius_mean', 'perimeter_mean', 'area_mean']]
y = data['diagnosis']
# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Create a decision tree classifier
clf = DecisionTreeClassifier()
# Fit the model to the training data
clf.fit(X_train, y_train)
# Perform predictions on the test data
y_pred = clf.predict(X_test)
# Calculate the accuracy of the model
accuracy = accuracy_score(y_test, y_pred)
34
FML_LAB FILE
print("Accuracy:", accuracy)
# Create a confusion matrix
confusion_mat = confusion_matrix(y_test, y_pred)
print("Confusion Matrix:")
print(confusion_mat)
OUTPUT:
LEARNING OUTCOMES:
35
FML_LAB FILE
36
