Line chart-

import [Link] as plt

# Data
days = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat']

temperatures = [30, 32, 31, 35, 34, 36]

# Find maximum temperature and its index

max_temp = max(temperatures)
max_index = [Link](max_temp)

# Create the plot

fig, ax = [Link](figsize=(10, 6))

# Plot line chart with custom color, style, and marker

[Link](days, temperatures,

color='darkorange',

linestyle='-.',
linewidth=2.5,

marker='^',
markersize=10,

markerfacecolor='red',

markeredgecolor='darkred',
markeredgewidth=1.5,

label='Daily Temperature (°C)')

# Label axes

ax.set_xlabel('Day', fontsize=13, fontweight='bold')

ax.set_ylabel('Temperature (°C)', fontsize=13, fontweight='bold')

# Add title
ax.set_title('Daily Temperature Data - Line Chart', fontsize=15,
fontweight='bold')
# Set Y-axis range for better visibility

ax.set_ylim(28, 38)

# Display grid lines

[Link](True, linestyle='--', alpha=0.6, color='gray')

# Highlight maximum temperature with annotation

[Link](f'Max Temp: {max_temp}°C',

xy=(days[max_index], max_temp),

xytext=(days[max_index], max_temp + 0.8),

arrowprops=dict(arrowstyle='->', color='blue', lw=2),

fontsize=11,
color='blue',

fontweight='bold',
ha='center')
# Add legend

[Link](fontsize=11, loc='upper left')

plt.tight_layout()

[Link]('daily_temperature_chart.png', dpi=150)

[Link]()
Pie chart-
import [Link] as plt

# Data
streams = ['Science', 'Commerce', 'Arts', 'IT']

students = [120, 100, 80, 60]

# Find the largest slice index (Science = 120)

max_index = [Link](max(students))
# Explode the largest slice

explode = [0.1 if i == max_index else 0 for i in range(len(students))]

# Custom colors for each slice

colors = ['#4C72B0', '#55A868', '#C44E52', '#FF9F00']

# Create the plot

fig, ax = [Link](figsize=(8, 8))

# Plot pie chart

wedges, texts, autotexts = [Link](

students,
labels=streams,

autopct='%1.1f%%',

explode=explode,
colors=colors,

startangle=140,

pctdistance=0.75,

wedgeprops=dict(edgecolor='white', linewidth=2),

shadow=True)
# Customize label fonts
for text in texts:

text.set_fontsize(13)
text.set_fontweight('bold')

# Customize percentage fonts

for autotext in autotexts:

autotext.set_fontsize(11)
autotext.set_fontweight('bold')

autotext.set_color('white')
ax.set_title('Student Distribution by Stream',

fontsize=16,

fontweight='bold',

pad=20)

# Add legend
[Link](

wedges,
[f'{s} ({n} students)' for s, n in zip(streams, students)],

title='Streams',

title_fontsize=12,
fontsize=11,

loc='lower left',

bbox_to_anchor=(0.0, -0.05))

plt.tight_layout()

[Link]('student_stream_piechart.png', dpi=150, bbox_inches='tight')

[Link]()
Bar chart-import [Link] as plt
import numpy as np

# Data
sources = ['Electricity', 'Gas', 'Solar', 'Others']

units = [300, 150, 100, 50]

# Custom colors
colors = ['#F4D03F', '#E67E22', '#2ECC71', '#95A5A6']
# Find maximum value index

max_index = [Link](max(units))
# Create the plot

fig, ax = [Link](figsize=(10, 6))

# Plot bar chart

bars = [Link](sources, units,

color=colors,
edgecolor='black',

linewidth=1.2,
width=0.5)

# Add value labels on top of each bar

for i, bar in enumerate(bars):

height = bar.get_height()

[Link](bar.get_x() + bar.get_width() / 2,

height + 5,

f'{height} units',

ha='center', va='bottom',
fontsize=11, fontweight='bold', color='black')
# Highlight the largest bar with annotation
[Link]('Highest Consumption',

xy=(sources[max_index], units[max_index]),
xytext=(sources[max_index], units[max_index] + 30),

arrowprops=dict(arrowstyle='->', color='red', lw=2),

fontsize=11, color='red', fontweight='bold',

ha='center')
# Label axes

ax.set_xlabel('Energy Source', fontsize=13, fontweight='bold')

ax.set_ylabel('Units Consumed', fontsize=13, fontweight='bold')

# Title
ax.set_title('Daily Energy Consumption by Source', fontsize=15,
fontweight='bold')
# Grid lines on Y-axis

[Link](True, linestyle='--', alpha=0.7, color='gray')

ax.set_axisbelow(True)
# Y-axis range

ax.set_ylim(0, 370)
# Legend

[Link](bars, sources, title='Energy Sources',

title_fontsize=11, fontsize=10, loc='upper right')

plt.tight_layout()

[Link]('energy_bar_chart.png', dpi=150)
[Link]()
Histogram-import [Link] as plt
import numpy as np

# Simulated energy consumption data (expanded for histogram distribution)

[Link](42)

electricity = [Link](300, 30, 200) # mean=300, std=30

gas = [Link](150, 20, 200)

solar = [Link](100, 15, 200)
others = [Link](50, 10, 200)

# Combine all into one dataset

all_units = [Link]([electricity, gas, solar, others])

# Create the plot

fig, axes = [Link](2, 2, figsize=(12, 9))

[Link]('Daily Energy Consumption — Histogram Distribution',

fontsize=16, fontweight='bold', y=1.01)

datasets = [electricity, gas, solar, others]

names = ['Electricity', 'Gas', 'Solar', 'Others']

colors = ['#F4D03F', '#E67E22', '#2ECC71', '#95A5A6']

mean_vals = [300, 150, 100, 50]

for ax, data, name, color, mean in zip([Link](), datasets, names, colors,
mean_vals):

# Plot histogram

[Link](data, bins=20, color=color, edgecolor='black',

linewidth=0.8, alpha=0.85, label=name)

# Add mean line
[Link](mean, color='red', linestyle='--', linewidth=2, label=f'Mean =
{mean}')
 # Labels and title

ax.set_title(f'{name} Consumption', fontsize=13, fontweight='bold')

ax.set_xlabel('Units Consumed', fontsize=11)

ax.set_ylabel('Frequency', fontsize=11)

# Grid
[Link](True, linestyle=':', alpha=0.6)

ax.set_axisbelow(True)

# Legend

[Link](fontsize=10)

plt.tight_layout()
[Link]('energy_histogram.png', dpi=150, bbox_inches='tight')

[Link]()
Scatter plot-import [Link] as plt
import numpy as np

# Simulated hourly energy consumption data (24 hours)

[Link](42)

hours = [Link](1, 25) # Hours 1 to 24

# Simulate consumption values around base means with variation

electricity = [Link](300, 40, 24)
gas = [Link](150, 25, 24)

solar = [Link](100, 20, 24)

others = [Link](50, 10, 24)

# Colors and markers for each source

sources = ['Electricity', 'Gas', 'Solar', 'Others']

datasets = [electricity, gas, solar, others]

colors = ['#F4D03F', '#E67E22', '#2ECC71', '#95A5A6']

markers = ['o', 's', '^', 'D']

# Create the plot

fig, ax = [Link](figsize=(13, 7))

for data, name, color, marker in zip(datasets, sources, colors, markers):

[Link](hours, data,
label=name,

color=color,

marker=marker,

s=100, # Marker size

edgecolors='black',
linewidths=0.8, alpha=0.85)
 # Add trend line for each source
z = [Link](hours, data, 1)

p = np.poly1d(z)
[Link](hours, p(hours),

color=color,

linestyle='--',
linewidth=1.5,
alpha=0.7)

# Highlight overall maximum point

all_data = [Link](datasets)

all_hours = [Link](hours, len(datasets))

max_idx = [Link](all_data)

max_hour = all_hours[max_idx]

max_val = all_data[max_idx]
[Link](f'Peak: {max_val:.1f} units\n(Hour {max_hour})',

xy=(max_hour, max_val),
xytext=(max_hour + 1.5, max_val + 10),

arrowprops=dict(arrowstyle='->', color='red', lw=2),

fontsize=10, color='red', fontweight='bold',

bbox=dict(boxstyle='round,pad=0.3', fc='lightyellow', ec='red'))

# Axes labels

ax.set_xlabel('Hour of the Day', fontsize=13, fontweight='bold')

ax.set_ylabel('Units Consumed', fontsize=13, fontweight='bold')

ax.set_title('Daily Energy Consumption — Scatter Plot (Hourly)',

fontsize=15, fontweight='bold')
# X-axis ticks for all 24 hours

ax.set_xticks(hours)
ax.set_xticklabels([f'{h}:00' for h in hours], rotation=45, fontsize=9)

# Grid

[Link](True, linestyle='--', alpha=0.5, color='gray')

ax.set_axisbelow(True)
# Legend

[Link](title='Energy Sources', title_fontsize=12,

fontsize=11, loc='upper right')

plt.tight_layout()

[Link]('energy_scatter_plot.png', dpi=150, bbox_inches='tight')

[Link]()
Eda code-
import pandas as pd

import numpy as np
import [Link] as plt

# Load Dataset

df = pd.read_csv("[Link]")
print(df)
print("Shape of dataset:", [Link])

print("\nColumns:", [Link]())
print("\nData Types:\n", [Link])

# First 5 rows

print("\nFirst 5 rows:\n", [Link]())

# Last 5 rows

print("\nLast 5 rows:\n", [Link]())

# Check missing values

print("\nMissing Values:\n", [Link]().sum())

# Option 1: Mean Imputation (for normally distributed data)

df['Calories'] = df['Calories'].fillna(df['Calories'].mean())

# Option 2: Median Imputation (preferred when outliers exist)

df['Calories'] = df['Calories'].fillna(df['Calories'].median())

# Option 3: Drop rows with missing values (only if very few)

df = [Link]()

# Verify after imputation

print("\nMissing values after imputation:\n", [Link]().sum())

print("\nSummary Statistics:\n", [Link]())
for column in [Link]:
Q1 = df[column].quantile(0.25)

Q3 = df[column].quantile(0.75)
IQR = Q3 - Q1

lower = Q1 - 1.5 * IQR

upper = Q3 + 1.5 * IQR

outliers = df[(df[column] < lower) | (df[column] > upper)]
print(f"\nOutliers in {column}: {len(outliers)}")

# Method 1: All columns at once

[Link]()

[Link]("Histograms of Features")

plt.tight_layout()

[Link]()

# Single column boxplot

[Link]()

[Link](df['Calories'])
[Link]("Boxplot of Calories")

[Link]("Calories")

[Link]()
# Combined boxplot for two columns

[Link]()

[Link]([df['Calories'].dropna(), df['Maxpulse']])

[Link]([1, 2], ['Calories', 'Maxpulse'])

[Link]("Boxplot of Calories and Maxpulse")

[Link]("Values"),[Link]()
correlation = [Link]()

print("\nCorrelation Matrix:\n", correlation)

[Link](figsize=(8, 6))

[Link]([Link], cmap='coolwarm', aspect='auto')

[Link]()

[Link](range(len([Link])), [Link], rotation=45)

[Link](range(len([Link])), [Link])

[Link]("Correlation Heatmap")

plt.tight_layout()

[Link]()

# Duration vs Calories

[Link]()

[Link](df['Duration'], df['Calories'], color='tomato', edgecolors='black', alpha=0.7)

[Link]("Duration")

[Link]("Calories")

[Link]("Duration vs Calories")

[Link](True, linestyle='--', alpha=0.5)

[Link]()

# Pulse vs Calories

[Link]()

[Link](df['Pulse'], df['Calories'], color='steelblue', edgecolors='black', alpha=0.7)

[Link]("Pulse")

[Link]("Calories")

[Link]("Pulse vs Calories")

[Link](True, linestyle='--', alpha=0.5)

[Link]()
print("\nCleaned Data:\n", [Link]())