Data Visualisation with Python

import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px
import pandas as pd

# Global style settings
plt.style.use('seaborn-v0_8-whitegrid')
sns.set_palette('Set2')

# Monthly revenue trend (matplotlib)
fig, ax = plt.subplots(figsize=(12, 5))
ax.plot(monthly['month'], monthly['revenue'], marker='o', linewidth=2, color='#059669')
ax.fill_between(monthly['month'], monthly['revenue'], alpha=0.1, color='#059669')
ax.set_title('Monthly Revenue Trend', fontsize=14, fontweight='bold')
ax.set_xlabel('Month')
ax.set_ylabel('Revenue ($)')
plt.xticks(rotation=45, ha='right')
plt.tight_layout()
plt.savefig('monthly_trend.png', dpi=150, bbox_inches='tight')
plt.show()

# Interactive with Plotly (much simpler)
fig = px.line(monthly, x='month', y='revenue',
              title='Monthly Revenue Trend',
              markers=True)
fig.show()

# Horizontal bar chart (better for many categories)
top_countries = df.groupby('country')['revenue'].sum().nlargest(10).reset_index()

fig, ax = plt.subplots(figsize=(10, 6))
bars = ax.barh(top_countries['country'], top_countries['revenue'], color='#059669')
ax.set_title('Revenue by Country (Top 10)', fontsize=14, fontweight='bold')
ax.set_xlabel('Total Revenue ($)')
# Add value labels
for bar in bars:
    ax.text(bar.get_width(), bar.get_y() + bar.get_height()/2,
            f'${bar.get_width():,.0f}', va='center', ha='left', fontsize=9)
plt.tight_layout()
plt.show()

# Grouped bar chart (compare two metrics across categories)
fig = px.bar(country_data, x='country', y=['revenue', 'orders'],
             barmode='group', title='Revenue and Orders by Country')
fig.show()

# Distribution of order amounts
fig, axes = plt.subplots(1, 2, figsize=(14, 5))

# Histogram
sns.histplot(df['amount'], bins=50, kde=True, ax=axes[0], color='#059669')
axes[0].set_title('Distribution of Order Amounts')
axes[0].set_xlabel('Amount ($)')

# Box plot by segment
sns.boxplot(data=df, x='segment', y='amount', ax=axes[1])
axes[1].set_title('Amount Distribution by Segment')
axes[1].set_xlabel('Segment')
axes[1].set_ylabel('Amount ($)')

plt.tight_layout()
plt.show()

# Violin plot (shows distribution shape AND box plot stats)
sns.violinplot(data=df, x='segment', y='amount')
plt.title('Order Amount Distribution by Segment')
plt.show()

# Scatter plot with colour coding
fig = px.scatter(df,
                 x='orders',
                 y='revenue',
                 color='country',
                 size='discount',
                 hover_data=['customer_name'],
                 title='Orders vs Revenue by Country')
fig.show()

# Seaborn scatter with regression line
sns.lmplot(data=df, x='orders', y='revenue',
           hue='segment',
           scatter_kws={'alpha': 0.4},
           line_kws={'linewidth': 2})
plt.title('Orders vs Revenue with Trend Lines by Segment')
plt.show()

# Correlation heatmap
numeric_cols = df.select_dtypes(include='number').columns
corr_matrix = df[numeric_cols].corr()

fig, ax = plt.subplots(figsize=(10, 8))
sns.heatmap(corr_matrix,
            annot=True,
            fmt='.2f',
            cmap='RdYlGn',
            center=0,
            ax=ax,
            linewidths=0.5)
ax.set_title('Correlation Matrix')
plt.tight_layout()
plt.show()

# Pivot heatmap (e.g., revenue by month and category)
pivot = df.pivot_table(values='revenue', index='category', columns='month_name', aggfunc='sum')
sns.heatmap(pivot, annot=True, fmt=',.0f', cmap='YlOrRd')
plt.title('Revenue by Category and Month')
plt.show()

# Professional chart template
fig, ax = plt.subplots(figsize=(12, 6))

# Plot data
ax.plot(x, y, color='#059669', linewidth=2, marker='o', markersize=4)

# Title and labels
ax.set_title('Clear, Descriptive Title', fontsize=14, fontweight='bold', pad=15)
ax.set_xlabel('X Axis Label (unit)', fontsize=11)
ax.set_ylabel('Y Axis Label (unit)', fontsize=11)

# Clean the spines (borders)
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)

# Format y-axis as currency
import matplotlib.ticker as mticker
ax.yaxis.set_major_formatter(mticker.FuncFormatter(lambda x, p: f'${x:,.0f}'))

# Annotate key points
ax.annotate('Key Event', xy=(peak_x, peak_y),
            xytext=(peak_x + 1, peak_y * 1.1),
            arrowprops=dict(arrowstyle='->', color='red'),
            color='red')

plt.tight_layout()
plt.savefig('chart.png', dpi=150, bbox_inches='tight')
plt.show()

import pandas as pd, matplotlib.pyplot as plt, seaborn as sns
url = 'https://raw.githubusercontent.com/datasciencedojo/datasets/master/titanic.csv'
df = pd.read_csv(url)

fig, axes = plt.subplots(2, 2, figsize=(14, 10))
fig.suptitle('Titanic Dataset Analysis', fontsize=16, fontweight='bold')

# 1. Distribution of passenger ages (histogram)
sns.histplot(df['Age'].dropna(), bins=30, ax=axes[0, 0], color='steelblue')
axes[0, 0].set_title('Age Distribution')

# 2. Survival rate by passenger class (bar chart)
survival_by_class = df.groupby('Pclass')['Survived'].mean() * 100
survival_by_class.plot(kind='bar', ax=axes[0, 1], color=['#EF4444','#F59E0B','#059669'])
axes[0, 1].set_title('Survival Rate by Class')
axes[0, 1].set_ylabel('Survival Rate (%)')

# 3. Fare distribution by class (box plot)
sns.boxplot(data=df, x='Pclass', y='Fare', ax=axes[1, 0])
axes[1, 0].set_title('Fare by Passenger Class')

# 4. Correlation heatmap
sns.heatmap(df[['Age','Fare','Survived','Pclass']].corr(),
            annot=True, fmt='.2f', ax=axes[1, 1], cmap='RdYlGn', center=0)
axes[1, 1].set_title('Correlation Matrix')

plt.tight_layout()
plt.savefig('titanic_eda.png', dpi=150)
plt.show()