import numpy as np

arr = np.array([1, 2, 3, 4])
print(arr + 5)

[6 7 8 9]

import matplotlib.pyplot as plt

marks = [80, 70, 90, 85]
students = ["A", "B", "C", "D"]

plt.bar(students, marks)
plt.title("Student Marks")
plt.show()

import pandas as pd

data = {
    "Name": ["Karma", "Sonam"],
    "Marks": [85, 92]
}

df = pd.DataFrame(data)
print(df)

    Name  Marks
0  Karma     85
1  Sonam     92

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
from matplotlib.sankey import Sankey
import plotly.graph_objects as go

# Load CSV
df = pd.read_csv('datasets/youtube_video.csv')

# === 1. Scatter Plot: Views vs Likes ===
plt.figure()
plt.scatter(df['view_count'], df['like_count'])
plt.xlabel('View Count')
plt.ylabel('Like Count')
plt.title('Views vs Likes')
plt.show()

# === 2. Bar Chart: Top 10 Videos by View Count ===
top = df.nlargest(10, 'view_count')

plt.figure()
plt.bar(np.arange(len(top)), top['view_count'])
plt.xticks(np.arange(len(top)), top['title'], rotation=90)
plt.ylabel('View Count')
plt.title('Top 10 Videos by View Count')
plt.tight_layout()
plt.show()

/tmp/ipykernel_2246/622102809.py:20: UserWarning: Tight layout not applied. The bottom and top margins cannot be made large enough to accommodate all Axes decorations.
  plt.tight_layout()

# Load CSV
df = pd.read_csv('datasets/youtube_video.csv')

# Convert published_date to datetime
df['published_date'] = pd.to_datetime(df['published_date'], errors='coerce')


# =========================================================
# 1. Histogram of View Counts
# =========================================================
plt.figure()
plt.hist(df['view_count'].dropna())
plt.xlabel('View Count')
plt.ylabel('Frequency')
plt.title('Distribution of View Counts')
plt.show()


# =========================================================
# 2. Scatter Plot – Likes vs Comments
# =========================================================
plt.figure()
plt.scatter(df['like_count'], df['comment_count'])
plt.xlabel('Like Count')
plt.ylabel('Comment Count')
plt.title('Likes vs Comments')
plt.show()


# =========================================================
# 3. Line Plot – Views Over Time
# =========================================================
df_sorted = df.sort_values('published_date')

plt.figure()
plt.plot(df_sorted['published_date'], df_sorted['view_count'])
plt.xlabel('Published Date')
plt.ylabel('View Count')
plt.title('Views Over Time')
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()

# Load your CSV
df = pd.read_csv('datasets/youtube_video.csv')

# Aggregate numbers
total_views = df['view_count'].sum()
total_likes = df['like_count'].sum()
total_comments = df['comment_count'].sum()

# Matplotlib Sankey Diagram
plt.figure(figsize=(10, 6))

sankey = Sankey(unit=None)  # no units displayed

sankey.add(
    flows=[total_views, -total_likes, 0],  # Views → Likes
    labels=['Total Views', 'Total Likes', ''],
    orientations=[0, 0, 0]
)

sankey.add(
    flows=[total_likes, -total_comments],  # Likes → Comments
    labels=['', 'Total Comments'],
    orientations=[0, 0],
    prior=0,  # connect to the previous sankey group
    connect=(1, 0)
)

diagrams = sankey.finish()
plt.title("YouTube Engagement Flow: Views → Likes → Comments")
plt.show()

<Figure size 1000x600 with 0 Axes>

Ignoring fixed x limits to fulfill fixed data aspect with adjustable data limits.

df = pd.read_csv('datasets/youtube_video.csv')

total_views = df['view_count'].sum()
total_likes = df['like_count'].sum()
total_comments = df['comment_count'].sum()

nodes = ["Views", "Likes", "Comments"]

source = [0, 1]
target = [1, 2]
value = [total_likes, total_comments]

fig = go.Figure(data=[go.Sankey(
    node=dict(
        label=nodes,
        pad=25,
        thickness=20
    ),
    link=dict(
        source=source,
        target=target,
        value=value
    )
)])

fig.update_layout(title_text="YouTube Engagement Flow (Views → Likes → Comments)", font_size=12)
fig

Session2: Tools Orientation 20/11/2025¶

Numpy¶

Matplotlib¶

Pandas¶

Assignment-01¶

Sankey Diagram¶