202001103042
Arjan Singh Johar
Btech – 1
Practical No – 01
Aim – Introduction to R tool for data analytics science.
Code –
Program 1 –
42+18
Arjan = 3042
class(Arjan)
print(Arjan)
print("Hello")
class(Arjan)
b=100L
class(b)
s="Afaf loves to do programming"
print(s)
class(s)
Arjan=as.integer()
class(Arjan)
x=c(42,38,52,44)
print(sqrt(x))
print(mean(x))
print(median(x))
x1=c("Arjan","Afaf","Saim","Abdul")
print(x1)
y=c(42,NA,38,NA,52,NA,44)
print(mean(y,na.rm=TRUE))
202001103042
Arjan Singh Johar
Btech – 1
Output –
202001103042
Arjan Singh Johar
Btech – 1
Program 2 –
stud_data =
data.frame(Name=c("Afaf","Arjan","Abdul"),PRN=c(38,42,44),Marks=c(100,89,89))
stud_data
a=20
b=40
if (a>b){
print("a is greater")
}else
print("b is greater")
x=c(1,2,3,4,5)
sum=0
for (i in x){
sum=sum+i
}
print(sum)
print(sum(x))
Output –
202001103042
Arjan Singh Johar
Btech – 1
Practical No – 02
Aim – Programs for Basic Statistics and Visualization in R
Code –
Program 1 –
x=c(10,20,30,40,50,60)
labels=c("Arjan","Abhishek","Abdul","Afaf","Saim","Pranav")
color=c("red","green","blue","orange","purple","yellow")
pie(x,labels,col = color,main="Marks Pie Chart")
legend("topright", labels, cex = 0.8, bty = "n", fill = rainbow(length(labels)))
hist(x,col="red",main="Sample Histogram")
Output –
202001103042
Arjan Singh Johar
Btech – 1
Program 2 –
#histogram
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
samples=np.random.randint(1,100,50)
plt.hist(samples)
plt.show()
#Pie chart
slices=[70,40,50,69,35]
lang=["JAVA","C++","PYTHON","C","R"]
cols=["Red","Green","Blue","Orange","Yellow"]
plt.pie(slices,labels=lang,colors=cols,autopct="%0.2f%%",explode=[0.5,0,0,0,0])
plt.show()
#histogram
import matplotlib.pyplot as plt
import numpy as np
x = (10,20,15,14,12,25,22,11,30,35)
plt.hist(x,color="Blue")
plt.show()
import matplotlib.pyplot as plt
categories = ['Category 1', 'Category 2', 'Category 3', 'Category 4']
values = [25, 40, 30, 50]
plt.bar(categories, values)
plt.xlabel('Categories')
plt.ylabel('Values')
plt.title('Bar Plot Example')
plt.show()
import seaborn as sns
import matplotlib.pyplot as plt
sns.get_dataset_names()
tips=sns.load_dataset('tips')
tips.head()
x=[1,2,3,4,5]
plt.boxplot(x)
import seaborn as sns
202001103042
Arjan Singh Johar
Btech – 1
import matplotlib.pyplot as plt
sns.get_dataset_names()
titanic=sns.load_dataset('titanic')
titanic.head()
sns.scatterplot(x='sex',y='age',data=titanic,hue='alone')
import matplotlib.pyplot as plt
import seaborn as sns
x=[1,2,3,4,5]
y=[10,20,30,40,50]
sns.pointplot(x=x,y=y)
import sklearn
from sklearn.datasets import load_diabetes
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
diabetes = load_diabetes()
column_name = diabetes.feature_names
df_diabetes = pd.DataFrame(diabetes.data)
df_diabetes .columns = column_name
df_diabetes .head()
print("Old Shape: ", df_diabetes.shape)
Q1 = df_diabetes['bmi'].quantile(0.25)
Q3 = df_diabetes['bmi'].quantile(0.75)
IQR = Q3 - Q1
lower = Q1 - 1.5*IQR
upper = Q3 + 1.5*IQR
upper_array = np.where(df_diabetes['bmi']>=upper)[0]
lower_array = np.where(df_diabetes['bmi']<=lower)[0]
df_diabetes.drop(index=upper_array, inplace=True)
df_diabetes.drop(index=lower_array, inplace=True)
print("New Shape: ", df_diabetes.shape)
plt.figure(figsize=(10, 5))
plt.subplot(1, 2, 1)
plt.boxplot(df_diabetes['bmi'], vert=False)
plt.title('Before Removing Outliers')
plt.xlabel('BMI')
plt.subplot(1, 2, 2)
plt.boxplot(diabetes.data[:, np.where(df_diabetes.columns == 'bmi')[0]], vert=False)
plt.title('After Removing Outliers')
plt.xlabel('BMI')
plt.tight_layout()
plt.show()
202001103042
Arjan Singh Johar
Btech – 1
Output –
Practical No – 03
Aim
–
202001103042
Arjan Singh Johar
Btech – 1
Program for simple linear regression is an approach for predicting a response using a
single multiple feature.
Code –
Program 1 –
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
data=pd.read_csv("Salary_Data.csv")
data.head()
data.info()
model = LinearRegression()
x = data[['YearsExperience']]
y = data['Salary']
x_train,x_test,y_train,y_test = train_test_split(x,y,train_size=0.8,random_state=0)
len(x_train)
len(x_test)
len(y_train)
len(y_test)
model.fit(x_train,y=y_train)
y_pred = model.predict(x_test)
plt.scatter(x_test,y_test,color='red',s=100)
plt.scatter(x_test,y_pred,color='blue',s=100)
plt.plot(x_test,y_pred,color='blue',linestyle="dotted")
from sklearn.metrics import r2_score
score=r2_score(y_test,y_pred)
score*100
Output –
202001103042
Arjan Singh Johar
Btech – 1
Program 2 –
import pandas as pd
import matplotlib.pyplot
as plt
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
data=pd.read_csv("train.csv")
data.head()
data.info()
model = LinearRegression()
x = data[['distance_traveled']]
y = data['fare']
x_train,x_test,y_train,y_test = train_test_split(x,y,train_size=0.8,random_state=0)
len(x_train)
len(x_test)
len(y_train)
len(y_test)
model.fit(x_train,y=y_train)
y_pred = model.predict(x_test)
y_pred
plt.scatter(x_test,y_test,color='red',s=100)
plt.scatter(x_test,y_pred,color='blue',s=100)
plt.plot(x_test,y_pred,color='blue',linestyle="dotted")
from sklearn.metrics import r2_score
score=r2_score(y_test,y_pred)
score*100
Output –
202001103042
Arjan Singh Johar
Btech – 1
Practical No – 04
202001103042
Arjan Singh Johar
Btech – 1
Aim – Program for predicting whether a user will purchase the product or not, using
logistic Regression.
Code –
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
data=pd.read_csv('Titanic-Dataset.csv')
data.head(5)
sns.countplot(x=data['Pclass'],hue=data['Survived'])
data.info()
mean_age = round((data['Age'].mean()),2)
data['Age'] = data['Age'].fillna(mean_age)
data.info()
col = ['PassengerId','Name','Cabin','Ticket','Fare']
data = data.drop(col , axis = 1)
data.head(5)
data.isnull().sum()
data = data.drop('Embarked' , axis = 1)
from sklearn.preprocessing import LabelEncoder
Encoder = LabelEncoder()
data['Sex'] = Encoder.fit_transform(data['Sex'])
data.head()
from sklearn.model_selection import train_test_split
x_train , x_test , y_train , y_test = train_test_split(x , y , train_size = 0.8 ,
random_state = 0)
len(x_train)
len(x_test)
x_test
from sklearn.linear_model import LogisticRegression
model = LogisticRegression()
model.fit(x_train,y_train)
y_pred = model.predict(x_test)
y_pred
y_test
from sklearn.metrics import accuracy_score
accuracy = accuracy_score(y_test , y_pred)
accuracy*100
model.predict([[1,0,31.0,1,0]])
202001103042
Arjan Singh Johar
Btech – 1
Output –
202001103042
Arjan Singh Johar
Btech – 1
Practical No – 05
Aim – Write a program to implement k-Nearest Neighbour algorithm to classify the
iris data set. Print both correct and wrong predictions
Program 1 – Titanic Dataset
Code –
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
data=pd.read_csv('Titanic-Dataset.csv')
data.head(5)
sns.countplot(x=data['Pclass'],hue=data['Survived'])
data.info()
mean_age = round((data['Age'].mean()),2)
data['Age'] = data['Age'].fillna(mean_age)
data.info()
col = ['PassengerId','Name','Cabin','Ticket','Fare']
data = data.drop(col , axis = 1)
data.head(5)
data.isnull().sum()
data = data.drop('Embarked' , axis = 1)
from sklearn.preprocessing import LabelEncoder
Encoder = LabelEncoder()
data['Sex'] = Encoder.fit_transform(data['Sex'])
data.head()
from sklearn.model_selection import train_test_split
x_train , x_test , y_train , y_test = train_test_split(x , y , train_size = 0.8 ,
random_state = 0)
len(x_train)
len(x_test)
x_test
from sklearn.neighbors import KNeighborsClassifier
model = KNeighborsClassifier(n_neighbors = 3)
model.fit(x_train , y_train)
y_pred = model.predict(x_test)
y_pred
y_test
from sklearn.metrics import accuracy_score
accuracy = accuracy_score(y_test , y_pred)
accuracy*100
202001103042
Arjan Singh Johar
Btech – 1
Output –
Program 2 – Iris Dataset
Code –
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
data=pd.read_csv('Iris.csv')
data.head(5)
data.info()
data.isnull().sum()
x = data.iloc[:, :-1].values
y = data.iloc[:, -1].values
from sklearn.model_selection import train_test_split
x_train , x_test , y_train , y_test = train_test_split(x , y ,
train_size = 0.8 , random_state = 0)
# len(x_train)
len(x_test)
from sklearn.neighbors import KNeighborsClassifier
model = KNeighborsClassifier(n_neighbors = 3)
model.fit(x_train , y_train)
y_pred = model.predict(x_test)
y_pred
y_test
from sklearn.metrics import accuracy_score
accuracy = accuracy_score(y_test , y_pred)
accuracy*100
model.predict()
202001103042
Arjan Singh Johar
Btech – 1
Output –
202001103042
Arjan Singh Johar
Btech – 1
Practical No – 06
Aim – For the given data perform ANOVA and tell the difference of variance between
groups.
Program –
Code –
# Load the ChickWeight dataset
data(ChickWeight)
# Subset the data to get the final weights
final_weight_data <- ChickWeight[ChickWeight$Time == max(ChickWeight$Time), ]
# Calculate the mean of final weights for each diet group
mean_weight <- tapply(final_weight_data$weight, final_weight_data$Diet, mean)
# Convert 'Diet' to a factor for ANOVA
final_weight_data$Diet <- factor(final_weight_data$Diet)
# Perform one-way ANOVA
anova_result <- aov(weight ~ Diet, data = final_weight_data)
# Post hoc test (Tukey's HSD)
tukey_result <- TukeyHSD(anova_result)
# Equality of variance (Levene's test)
library(car)
levene_test <- leveneTest(weight ~ Diet, data = final_weight_data)
print(levene_test)
# Create a boxplot
boxplot(weight ~ Diet, data = final_weight_data, main = "Boxplot of Final Weight by
Diet", xlab = "Diet", ylab = "Final Weight")
# Check the p-value from ANOVA
p_value <- summary(anova_result)[[1]][["Pr(>F)"]][1]
# Define the significance level (alpha)
alpha <- 0.05
202001103042
Arjan Singh Johar
Btech – 1
# Print the decision based on the p-value
if (p_value < alpha) {
cat("Reject the null hypothesis. There is a significant difference in means.\n")
} else {
cat("Accept the null hypothesis. There is no significant difference in means.\n")
}
Output –
202001103042
Arjan Singh Johar
Btech – 1
Practical No – 07
Aim – Implementation of Naive Bayesian Classifier.
Code and Output –
library(e1071)
# Load the Iris dataset
data(iris)
library(caret)
set.seed(123) # For reproducibility
train_index <- createDataPartition(iris$Species, p = 0.7, list = FALSE)
train_data <- iris[train_index, ]
test_data <- iris[-train_index, ]
# Train the Naive Bayes classifier
nb_classifier <- naiveBayes(Species ~ ., data = train_data)
# Predict on the test set
test_predictions <- predict(nb_classifier, newdata = test_data)
# Create a confusion matrix
confusion_matrix <- table(Actual = test_data$Species, Predicted = test_predictions)
confusion_matrix
# Calculate accuracy
accuracy <- sum(diag(confusion_matrix)) / sum(confusion_matrix)
accuracy
Output –
202001103042
Arjan Singh Johar
Btech – 1
Practical No – 08
Aim – Program for market basket analysis using Association Rules.
Program –
# Load the libraries
install.packages("arulesViz")
library(arules)
library(arulesViz)
library(datasets)
# Load the data set
data(Groceries)
# Create an item frequency plot for the top 20 items
itemFrequencyPlot(Groceries,topN=20,type="absolute")
# Get the rules
rules <- apriori(Groceries, parameter = list(supp = 0.001, conf = 0.8))
# Show the top 5 rules, but only 2 digits
options(digits=2)
inspect(rules[1:5])
rules<-sort(rules, by="confidence", decreasing=TRUE)
rules <- apriori(Groceries, parameter = list(supp = 0.001, conf = 0.8,maxlen=3))
subset.matrix <- is.subset(rules, rules)
subset.matrix[lower.tri(subset.matrix, diag=T)] <- NA
redundant <- colSums(subset.matrix, na.rm=T) >= 1
rules.pruned <- rules[!redundant]
rules<-rules.pruned
rules<-apriori(data=Groceries, parameter=list(supp=0.001,conf = 0.08),
appearance = list(default="lhs",rhs="whole milk"),
control = list(verbose=F))
202001103042
Arjan Singh Johar
Btech – 1
rules<-sort(rules, decreasing=TRUE,by="confidence")
inspect(rules[1:5])
library(arulesViz)
plot(rules,method="graph",interactive=TRUE)
Output –
202001103042
Arjan Singh Johar
Btech – 1
Practical No – 09
Aim – Program to implement a Decision tree algorithm for any application.
Code –
# Load the required libraries
library(rpart)
library(rpart.plot)
# Load the "mtcars" dataset (built-in dataset in R)
data(mtcars)
# Split the dataset into features (X) and target (y)
X <- mtcars[, -1] # Features (excluding the first column, which is the car model)
y <- mtcars$mpg # Target (miles per gallon)
# Build the decision tree model
model <- rpart(y ~ ., data = data.frame(X, y), method = "anova")
# Visualize the decision tree
rpart.plot(model, box.palette = "auto", type = 3, extra = 1)
Output –
202001103042
Arjan Singh Johar
Btech – 1
Practical No – 10
Aim – Program to Simulate Principal component analysis.
Code –
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_iris
from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB
# Load the Iris dataset
iris = load_iris()
X = iris.data
y = iris.target
# Standardize the features (mean=0 and variance=1)
X_standardized = StandardScaler().fit_transform(X)
# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X_standardized, y,
test_size=0.4, random_state=42)
# Create a Naive Bayes classifier
clf = GaussianNB()
# Train the classifier
clf.fit(X_train, y_train)
# Make predictions on the test data
predictions = clf.predict(X_test)
from sklearn.metrics import accuracy_score
accuracy_score(y_test, predictions)
pca = PCA(n_components=1)
X_pca = pca.fit_transform(X_standardized)
# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X_pca, y,
test_size=0.4, random_state=42)
# Create a Naive Bayes classifier
clf = GaussianNB()
# Train the classifier
clf.fit(X_train, y_train)
# Make predictions on the test data
predictions = clf.predict(X_test)
from sklearn.metrics import accuracy_score
202001103042
Arjan Singh Johar
Btech – 1
accuracy_score(y_test, predictions)
# Apply PCA and reduce the data to 2 principal components
pca = PCA(n_components=)
X_pca = pca.fit_transform(X_standardized)
# Print the explained variance ratio
print("Explained Variance Ratio (2 components):",
pca.explained_variance_ratio_)
# Plot the data points in the reduced feature space
plt.figure(figsize=(8, 6))
colors = ['blue', 'red', 'green']
for i, target_name in enumerate(iris.target_names):
plt.scatter(X_pca[y == i, 0], X_pca[y == i, 1], color=colors[i],
label=target_name)
plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')
plt.title('PCA on Iris Dataset')
plt.legend()
plt.show()
Output –
202001103042
Arjan Singh Johar
Btech – 1
Practical No – 11
Aim – Program to Simulate Principal component analysis
Code –
# Load the USArrests dataset
data("USArrests")
# Perform SVD on the dataset
svd_result <- svd(USArrests)
# Extract U, Sigma, and V matrices
U <- svd_result$u
Sigma <- diag(svd_result$d)
V <- svd_result$v
# Print the matrices
print("U (left singular vectors):")
print(U)
print("Sigma (singular values):")
print(Sigma)
print("V (right singular vectors):")
print(V)
Output –
202001103042
Arjan Singh Johar
Btech – 1
Practical No – 12
Aim – Using built-in function perform Support Vector machine algorithm
Code –
library(e1071)
data(iris)
set.seed(123) # for reproducibility
sample_indices <- sample(1:nrow(iris), nrow(iris) * 0.7) # 70% for training
train_data <- iris[sample_indices, ]
test_data <- iris[-sample_indices, ]
svm_model <- svm(Species ~ ., data = train_data, kernel = "linear")
predictions <- predict(svm_model, test_data)
confusion_matrix <- table(predictions, test_data$Species)
print(confusion_matrix)
print(predictions)
accuracy <- sum(diag(confusion_matrix)) / sum(confusion_matrix)
cat("Accuracy:", accuracy, "\n")
Output –
