MACHINE LEARING LAB RECORD

INDEX

SNO NAME OF PROGRAM DATE OF SUBMISSION

1 Find s algorithm

2 Mean mode variance

3 Median ,Standard deviation

4 Candidate elimination algorithm

5 Perceptron training

6 Simple linear regression

7 Multilinear regression

8 Id3 decision tree algorithm

9 Decision tree using GINI INDEX

10 KNN algorithm

11 K means algorithm

1
 MACHINE LEARING LAB RECORD

1. Find_s

Code:
import pandas as pd

df = pd.read_csv("EnjoySport.csv")

target = input("Enter the target column: ")

target_index = df.columns.get_loc(target)

h = None

for _, row in df.iterrows():

if str(row[target]).strip().lower() == 'yes':

current = row[:target_index].tolist()

if h is None:

h = current

else:

h = ['?' if h[j] != current[j] else h[j] for j in range(target_index)]

print("Current hypothesis:", h)

print(f"\nFinal specific hypothesis: {h}")

OUTPUT:

2
 MACHINE LEARING LAB RECORD

2.Mean Mode & Variance:

datap0543 = [4,8,6,5,3,7,6,7]

#mean

sump0543 = 0

i=0

n = len(datap0543)

while i < n:

sump0543 += datap0543[i]

i = i+1

mean = sump0543/n

print("Mean:",mean)

# mode/

c = []

for i in range(n):

c.append(0)

c[i] = datap0543.count(datap0543[i])

high = c[0]

while i in range(n):

if high < c[i]:

high = c[i]

i = i+1

mode = []

for i in range(n):

if c[i] == high:

3
 MACHINE LEARING LAB RECORD

mode.append(datap0543[i])

print("Mode:",set(mode))

# variance

num = 0

for i in range(n):

num =num + math.pow(datap0543[i]-mean,2)

var = num/n

print("Variance:",var)

OUTPUT:

3.Median & Standard deviation:

datap0543 = [4,8,6,5,3,7,6,7]

#mean

sump0543 = 0

i=0

n = len(datap0543)

while i < n:

sump0543 += datap0543[i]

i = i+1

4
 MACHINE LEARING LAB RECORD

mean = sump0543/n

print("Mean:",mean)

# median

if n%2==0:

median = (datap0543[int(n/2)]+datap0543[int(n/2 - 1)])/2

else:

median = datap0543[int(n/2)]

print("Median:",median)

# variance

num = 0

for i in range(n):

num =num + math.pow(datap0543[i]-mean,2)

var = num/n

print("Variance:",var)

# stddev

std = math.sqrt(var)

print("Standard Deviation:",std)

OUTPUT:

4.CandidateElimination:

5
 MACHINE LEARING LAB RECORD

Code:
import pandas as pd

df = pd.read_csv("EnjoySport.csv")

target = input("Enter target column: ").strip()

# Initialize Specific (S) and General (G) hypotheses

S = list(df.iloc[0, :-1])

G = [["?"] * len(S)]

print("\nInitial S:", S)

print("Initial G:", G)

# Iterate over dataset

for i, row in df.iterrows():

x = row.iloc[:-1]

y = row.loc[target] # Use .loc to access by label (avoid warning)

if str(y).lower() == "yes":

# Generalize S

S = ["?" if S[j] != x.iloc[j] else S[j] for j in range(len(S))]

# Remove inconsistent hypotheses from G

G = [g for g in G if all(g[j] == "?" or g[j] == x.iloc[j] for j in range(len(S)))]

else:

new_G = []

for g in G:

for j in range(len(S)):

if g[j] == "?" and S[j] != "?":

6
 MACHINE LEARING LAB RECORD

h = g.copy()

h[j] = S[j]

if any(h[k] != x.iloc[k] or h[k] == "?" for k in range(len(S))):

new_G.append(h)

# Add new consistent hypotheses

G = G + [h for h in new_G if h not in G]

print(f"\nAfter instance {i+1} ({y}):")

print("S:", S)

print("G:", G)

print("\nFinal S:", S)

print("Final G:", G)

OUTPUT:

5.Perceptron:
Code:
7
 MACHINE LEARING LAB RECORD

print("Give init weights")

w0 = float(input("w0:"))

w1 = float(input("w1:"))

w2 = float(input("w2:"))

n = float(input("Enter learning_rate:"))

x0 = -1

ch = int(input("Enter input OR:0 XOR=1 AND=2"))

if ch == 0:

inp = [[0,0,0],[0,1,1],[1,0,1],[1,1,1]]

elif ch == 1:

inp = [[0,0,1],[0,1,0],[1,0,0],[1,1,1]]

else:

inp = [[0,0,0],[0,1,0],[1,0,0],[1,1,1]]

i=0

while(i<len(inp)):

print("\n")

print(f"Iteration",i+1)

targ = inp[i][2]

x1 = inp[i][0]

x2 = inp[i][1]

y = w0*x0 + w1*x1 + w2*x2

i=i+1

y=1 if y>0 else 0

# check with target

if y == targ:

print("No need to update")

8
 MACHINE LEARING LAB RECORD

else:

w0 = w0 + n*(targ-y)*x0

w1 = w1 + n*(targ-y)*x1

w2 = w2 + n*(targ-y)*x2

print("Updated weights:")

print(f"w0:",w0,"\n","w1:",w1,"\n","w2:",w2,"\n")

OUTPUT:

6.Simple linear regression

9
 MACHINE LEARING LAB RECORD

import pandas as pd

import matplotlib.pyplot as plt

from sklearn.datasets import load_iris

from sklearn.linear_model import LinearRegression

from sklearn.model_selection import train_test_split

from sklearn.metrics import mean_squared_error

# Load the Iris dataset

iris = load_iris()

X = iris.data[:, 2].reshape(-1, 1) # Petal length (as input feature)

y = iris.data[:, 3]

# Split the data into training and testing sets

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

model = LinearRegression()

model.fit(X_train, y_train)

y_pred = model.predict(X_test)

# Calculate the mean squared error

mse = mean_squared_error(y_test, y_pred)

print(f"Mean Squared Error: {mse}")

# Visualizing the regression line and data points

plt.scatter(X_test, y_test, color='blue', label='Actual')

plt.plot(X_test, y_pred, color='red', label='Regression Line')

plt.xlabel('Petal Length')

plt.ylabel('Petal Width')

plt.title('Linear Regression on Iris Dataset (Petal Length vs Petal Width)')

10
 MACHINE LEARING LAB RECORD

plt.legend()

plt.show()

OUTPUT:

7.Multiple linear regression:

import pandas as pd

11
 MACHINE LEARING LAB RECORD

import matplotlib.pyplot as plt

from sklearn.datasets import load_iris

from sklearn.linear_model import LinearRegression

from sklearn.model_selection import train_test_split

from sklearn.metrics import mean_squared_error

iris = load_iris()

X = iris.data[:, [0, 1, 2]] # Sepal length, Sepal width, Petal length (multiple features)

y = iris.data[:, 3] # Petal width (target variable)

# Split the data into training and testing sets

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

model = LinearRegression()

model.fit(X_train, y_train)

y_pred = model.predict(X_test)

# Calculate the mean squared error

mse = mean_squared_error(y_test, y_pred)

print(f"Mean Squared Error: {mse}")

# Visualizing the actual vs predicted values

plt.scatter(y_test, y_pred)

plt.xlabel('Actual Petal Width')

plt.ylabel('Predicted Petal Width')

plt.title('Multiple Linear Regression: Actual vs Predicted')

plt.show()

# Display the coefficients and intercept

12
 MACHINE LEARING LAB RECORD

print("Coefficients:", model.coef_)

print("Intercept:", model.intercept_)

OUTPUT:

8.ID3:
Code:

import pandas as pd

import matplotlib.pyplot as plt

13
 MACHINE LEARING LAB RECORD

from sklearn.tree import DecisionTreeClassifier, plot_tree

df = pd.read_csv("play_tennis.csv")

print(df)

df_encoded = df.copy()

for col in df.columns:

df_encoded[col] = df[col].astype('category').cat.codes

x = df_encoded.drop("PlayTennis", axis=1)

y = df["PlayTennis"]

model = DecisionTreeClassifier(criterion="entropy", random_state=0)

model.fit(x, y)

plt.figure(figsize=(20, 12))

plot_tree(

model,

feature_names=x.columns.tolist(),

class_names=df["PlayTennis"].unique().tolist(),

filled=True,

rounded=True,

precision=2,

fontsize=12

plt.show()

14
 MACHINE LEARING LAB RECORD

OUTPUT:

8.GINI IMPURITY
Code
import pandas as pd

import matplotlib.pyplot as plt

from sklearn.tree import DecisionTreeClassifier, plot_tree

15
 MACHINE LEARING LAB RECORD

df = pd.read_csv("play_tennis.csv")

print(df)

df_encoded = df.copy()

for col in df.columns:

df_encoded[col] = df[col].astype('category').cat.codes

x = df_encoded.drop("PlayTennis", axis=1)

y = df["PlayTennis"]

model = DecisionTreeClassifier(criterion="gini", random_state=0)

model.fit(x, y)

plt.figure(figsize=(20, 12))

plot_tree(

model,

feature_names=x.columns.tolist(),

class_names=df["PlayTennis"].unique().tolist(),

filled=True,

rounded=True,

precision=2,

fontsize=12

plt.show()

16
 MACHINE LEARING LAB RECORD

OUTPUT:

10.KNN
Code
from sklearn.datasets import load_iris

from sklearn.model_selection import train_test_split

from sklearn.neighbors import KNeighborsClassifier

from sklearn.metrics import accuracy_score, classification_report

17
 MACHINE LEARING LAB RECORD

# Load the Iris dataset

iris = load_iris()

X = iris.data

y = iris.target

# Split the dataset into training and testing sets

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

#KNN classifier with k=3

knn = KNeighborsClassifier(n_neighbors=3)

# Fit the model on training data

knn.fit(X_train, y_train)

# Make predictions on test data

y_pred = knn.predict(X_test)

# Evaluate the model

print("Accuracy:", accuracy_score(y_test, y_pred))

print("\nClassification Report:\n", classification_report(y_test, y_pred))

OUTPUT

18
 MACHINE LEARING LAB RECORD

11.K-MEANS ALGORITHM
Code
from sklearn.datasets import load_iris

from sklearn.cluster import KMeans

import matplotlib.pyplot as plt

from sklearn.decomposition import PCA

# Load the Iris dataset

iris = load_iris()

X = iris.data

# Create KMeans model with 3 clusters (since Iris has 3 flower types)

kmeans = KMeans(n_clusters=3, random_state=42)

kmeans.fit(X)

# Predict cluster labels

labels = kmeans.labels_

19
 MACHINE LEARING LAB RECORD

# Reduce dimensionality for visualization

pca = PCA(n_components=2)

X_pca = pca.fit_transform(X)

plt.scatter(X_pca[:, 0], X_pca[:, 1], c=labels, cmap='viridis', marker='o', edgecolor='k')

plt.title("K-Means Clustering (Iris Dataset)")

plt.xlabel("Sepal length")

plt.ylabel("Sepal width")

plt.show()

OUTPUT

20