P-2
Write Python code to create a Pandas DataFrame using any sequence data type.
a) Display the DataFrame.+
b) Display first 5 records.
c) Display last 10 records.
d) Display the number of missing values in the dataset.
import pandas as pd
import numpy as np
# Create a list of dictionaries with some missing values
data = [
('Name': 'Alice', 'Age': 25, 'City': 'New York'),
('Name': 'Bob', 'Age': 30, 'City': 'Los Angeles'),
{'Name': 'Charlie', 'Age': 22, 'City': 'Chicago'}, ('Name': 'David', 'Age': None, 'City': 'Houston'), {'Name': 'Eva', 'Age': 28, 'City': None), ('Name': 'Frank', 'Age': 33, 'City': 'Seattle'), {'Name': 'Grace', 'Age': 27, 'City': 'Austin'}, ('Name': 'Helen', 'Age': np.nan, 'City': 'Boston'),
('Name': 'lan', 'Age': 24, 'City': 'Denver'),
('Name': 'Jane', 'Age': 29, 'City': None),
('Name': 'Kyle', 'Age': 31, 'City': 'Miami'}
#Create DataFrame
df = pd.DataFrame(data)
# a) Display the DataFrame
print("Full DataFrame:")
print(df)
#b) Display first 5 records
print("\nFirst 5 records:")
print(df.head())
#c) Display last 10 records
print("\nLast 10 records:")
print(df.tail(10))
#d) Display the number of missing values in the dataset
print("\nNumber of missing values in each column:")
print(df.isnull().sum())
P-7
from sklearn.linear_model import Linear Regression
# Data: Hours and corresponding marks
hours = [[1], [2], [3], [4], [5]]
marks = [35, 45, 50, 70, 75]
# Create the model
model = LinearRegression()
#Train the model
model.fit(hours, marks)
# Predict marks for 6 hours of study
predicted = model.predict([[6]])
# Show result
print("Predicted marks for 6 hours:", predicted[0])
P-5
import pandas as pd.
from sklearn.model_selection import train_test split
from sklearn.linear_model import Linear Regression
from sklearn.metrics import mean squared error
#sample dataset: precting marks based on hours studied
data={
'Hours': [1,2,3,4,5,6,7,8,3.5),
'Marks': [34,45,66,87,94,100,56,78,96]}
#create dataframe
df=pd.DataFrame(data)
#split data into feature and target
X= df[['Hours']]#feature
Y= df['Marks']#target
#split training and testing set into 80% and 20%
X_train,X_test,Y_train,Y_test =
train_test_split(X,Y, test_size=0.2, random_state=1)
model = Linear Regression()# create model
model.fit(X_train, Y_train)#train model
#make predictions
Y_pred model.predict(X_test)
#print prediction and actual
print("predicted marks",Y_pred)
print("Actual marks", Y_test.values)
#Evaluate model
mse = mean_squared_error(Y_test,Y_pred)
print("Mse", mse)
P -3
import numpy as np
arr = np.arange (30,41)
arr1, arr2 = np.array_split(arr,2)
print("First part",arr1)
print("Sec part",arr2)