import pandas as pd

import numpy as np # Step 4: Check for Duplicates

import matplotlib.pyplot as plt duplicates = df_read.duplicated().sum()

import seaborn as sns print(duplicates)

from sklearn.model_selection import train_test_split

from sklearn.linear_model import LinearRegression # Step 5: Check for Skew

from sklearn.metrics import mean_squared_error, skewness = df_read.skew()

r2_score
print(skewness)

# Create sample dataset for demonstration

# Step 6: Display Mean, Mode, Standard Deviation,
data = { and Variance

'A': [1, 5, 9, 13, np.nan, 21], mean_values = df_read.mean()

'B': [2, np.nan, 10, 14, 18, 22], mode_values = df_read.mode().iloc[0]

'C': [3, 7, 11, np.nan, 19, 23], std_dev = df_read.std()

'D': [4, 8, 12, 16, 20, 24] variance = df_read.var()

print("Mean Values:\n", mean_values)

# Create a DataFrame print("Mode Values:\n", mode_values)

df = pd.DataFrame(data) print("Standard Deviation:\n", std_dev)

print("Variance:\n", variance)

# Save to CSV

csv_file_path = 'sample_data.csv' # Step 7: Show Ways to Remove Null Values

df.to_csv(csv_file_path, index=False) df_dropped_rows = df_read.dropna()

df_dropped_columns = df_read.dropna(axis=1)

# Read the data from CSV file

df_read = pd.read_csv(csv_file_path) print("Dropped Rows:\n", df_dropped_rows)

print("Dropped Columns:\n", df_dropped_columns)

# Step 2: Show All Columns and Their Data Types

columns_and_types = df_read.dtypes # Step 8: Replace Null Values with Mean, Mode, and a
Certain Value
print(columns_and_types)
df_fill_mean = df_read.fillna(df_read.mean())

df_fill_mode = df_read.fillna(df_read.mode().iloc[0])
# Step 3: Check for Null Values
df_fill_value = df_read.fillna(0)
null_values = df_read.isnull().sum()

print(null_values)
print("Filled with Mean:\n", df_fill_mean)
print("Filled with Mode:\n", df_fill_mode) print("R-squared (R2) Score:", r2)

print("Filled with Value 0:\n", df_fill_value)

# Step 12: Plot the Relevant Results

# Step 9: Visualize the Dataset # Plot actual vs predicted values

sns.pairplot(df_read) plt.scatter(y_test, y_pred)

plt.show() plt.xlabel('Actual Values')

plt.ylabel('Predicted Values')

sns.heatmap(df_read.isnull(), cbar=False, plt.title('Actual vs Predicted Values')

cmap='viridis')
plt.show()
plt.show()

# Step 10: Choose an Appropriate Learning Model and

Justify

# Step 11: Compute Accuracy and Other Scores

# Prepare the data

df_filled = df_read.fillna(df_read.mean()) # Fill

missing values with mean for simplicity

X = df_filled[['A', 'B', 'C']]

y = df_filled['D']

# Split the data

X_train, X_test, y_train, y_test = train_test_split(X, y,

test_size=0.2, random_state=42)

# Train the model

model = LinearRegression()

model.fit(X_train, y_train)

# Predict

y_pred = model.predict(X_test)

# Compute scores

mse = mean_squared_error(y_test, y_pred)

r2 = r2_score(y_test, y_pred)

print("Mean Squared Error (MSE):", mse)

import pandas as pd

import numpy as np # Step 4: Check for Duplicates

import matplotlib.pyplot as plt duplicates = df_read.duplicated().sum()

import seaborn as sns print(duplicates)

from sklearn.model_selection import train_test_split

from sklearn.linear_model import LinearRegression # Step 5: Check for Skew

from sklearn.metrics import mean_squared_error, skewness = df_read.skew()

r2_score
print(skewness)

# Create sample dataset for demonstration

# Step 6: Display Mean, Mode, Standard Deviation,
data = { and Variance

'A': [1, 5, 9, 13, np.nan, 21], mean_values = df_read.mean()

'B': [2, np.nan, 10, 14, 18, 22], mode_values = df_read.mode().iloc[0]

'C': [3, 7, 11, np.nan, 19, 23], std_dev = df_read.std()

'D': [4, 8, 12, 16, 20, 24] variance = df_read.var()

print("Mean Values:\n", mean_values)

# Create a DataFrame print("Mode Values:\n", mode_values)

df = pd.DataFrame(data) print("Standard Deviation:\n", std_dev)

print("Variance:\n", variance)

# Save to CSV

csv_file_path = 'sample_data.csv' # Step 7: Show Ways to Remove Null Values

df.to_csv(csv_file_path, index=False) df_dropped_rows = df_read.dropna()

df_dropped_columns = df_read.dropna(axis=1)

# Read the data from CSV file

df_read = pd.read_csv(csv_file_path) print("Dropped Rows:\n", df_dropped_rows)

print("Dropped Columns:\n", df_dropped_columns)

# Step 2: Show All Columns and Their Data Types

columns_and_types = df_read.dtypes # Step 8: Replace Null Values with Mean, Mode, and a
Certain Value
print(columns_and_types)
df_fill_mean = df_read.fillna(df_read.mean())

df_fill_mode = df_read.fillna(df_read.mode().iloc[0])
# Step 3: Check for Null Values
df_fill_value = df_read.fillna(0)
null_values = df_read.isnull().sum()

print(null_values)
print("Filled with Mean:\n", df_fill_mean)
print("Filled with Mode:\n", df_fill_mode) print("R-squared (R2) Score:", r2)

print("Filled with Value 0:\n", df_fill_value)

# Step 12: Plot the Relevant Results

# Step 9: Visualize the Dataset # Plot actual vs predicted values

sns.pairplot(df_read) plt.scatter(y_test, y_pred)

plt.show() plt.xlabel('Actual Values')

plt.ylabel('Predicted Values')

sns.heatmap(df_read.isnull(), cbar=False, plt.title('Actual vs Predicted Values')

cmap='viridis')
plt.show()
plt.show()

# Step 10: Choose an Appropriate Learning Model and

Justify

# Step 11: Compute Accuracy and Other Scores

# Prepare the data

df_filled = df_read.fillna(df_read.mean()) # Fill

missing values with mean for simplicity

X = df_filled[['A', 'B', 'C']]

y = df_filled['D']

# Split the data

X_train, X_test, y_train, y_test = train_test_split(X, y,

test_size=0.2, random_state=42)

# Train the model

model = LinearRegression()

model.fit(X_train, y_train)

# Predict

y_pred = model.predict(X_test)

# Compute scores

mse = mean_squared_error(y_test, y_pred)

r2 = r2_score(y_test, y_pred)

print("Mean Squared Error (MSE):", mse)