Visualize Pandas DataFrames in Cursor in 12 Minutes

# Install Cursor (macOS)
brew install --cask cursor

# OR download from https://cursor.sh

# Verify Python environment
python --version  # Should be 3.10+
pip install pandas matplotlib seaborn

# analysis.py
import pandas as pd
import matplotlib.pyplot as plt

# Cursor needs this to display inline
plt.ion()  # Interactive mode for real-time updates

# Load sample data
df = pd.read_csv('sales_data.csv')
print(df.head())

# Cursor AI prompt examples (Cmd+K)

# 1. Quick distribution check
df['revenue']  # Select this line, then Cmd+K: "plot distribution"

# AI generates:
plt.figure(figsize=(10, 6))
plt.hist(df['revenue'], bins=30, edgecolor='black', alpha=0.7)
plt.title('Revenue Distribution')
plt.xlabel('Revenue ($)')
plt.ylabel('Frequency')
plt.show()

# 2. Time series with trend line
# Cmd+K: "plot revenue over time with moving average"

df['date'] = pd.to_datetime(df['date'])
df = df.sort_values('date')

plt.figure(figsize=(12, 6))
plt.plot(df['date'], df['revenue'], label='Actual', alpha=0.6)
# Rolling average smooths noise
plt.plot(df['date'], df['revenue'].rolling(window=7).mean(), 
         label='7-day MA', linewidth=2)
plt.legend()
plt.title('Revenue Trend')
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()

# 3. Category comparison
# Cmd+K: "compare average revenue by product category"

category_avg = df.groupby('category')['revenue'].mean().sort_values()

plt.figure(figsize=(10, 6))
category_avg.plot(kind='barh')  # Horizontal bars for readability
plt.title('Average Revenue by Category')
plt.xlabel('Average Revenue ($)')
plt.tight_layout()
plt.show()

# Common issues and AI fixes

# Issue: Overlapping labels
# Highlight problematic code, Cmd+K: "fix overlapping x-axis labels"

# Cursor adds:
plt.xticks(rotation=45, ha='right')  # ha='right' aligns text properly
plt.tight_layout()  # Prevents label cutoff

# Issue: Colors hard to distinguish
# Cmd+K: "use colorblind-friendly palette"

# Cursor imports and applies:
import seaborn as sns
colors = sns.color_palette('colorblind', n_colors=5)
plt.bar(x, y, color=colors)

# Issue: Legend blocking data
# Cmd+K: "move legend outside plot area"

plt.legend(bbox_to_anchor=(1.05, 1), loc='upper left')
plt.tight_layout()

# Cmd+K: "create 2x2 subplot grid showing revenue histogram, 
# time series, category bars, and correlation heatmap"

import seaborn as sns
import numpy as np

fig, axes = plt.subplots(2, 2, figsize=(15, 12))

# Top left: Distribution
axes[0, 0].hist(df['revenue'], bins=30, edgecolor='black')
axes[0, 0].set_title('Revenue Distribution')
axes[0, 0].set_xlabel('Revenue ($)')

# Top right: Time series
df_sorted = df.sort_values('date')
axes[0, 1].plot(df_sorted['date'], df_sorted['revenue'])
axes[0, 1].set_title('Revenue Over Time')
axes[0, 1].tick_params(axis='x', rotation=45)

# Bottom left: Category comparison
category_avg.plot(kind='barh', ax=axes[1, 0])
axes[1, 0].set_title('Avg Revenue by Category')

# Bottom right: Correlation heatmap
numeric_cols = df.select_dtypes(include=[np.number])
sns.heatmap(numeric_cols.corr(), annot=True, ax=axes[1, 1], 
            cmap='coolwarm', center=0)  # center=0 highlights +/- correlations
axes[1, 1].set_title('Feature Correlations')

plt.tight_layout()
plt.show()

# test_visualization.py
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

plt.ion()

# Generate test data
np.random.seed(42)
test_df = pd.DataFrame({
    'date': pd.date_range('2025-01-01', periods=100),
    'revenue': np.random.normal(50000, 15000, 100),
    'category': np.random.choice(['A', 'B', 'C'], 100)
})

# Quick visualization test
plt.figure(figsize=(10, 6))
plt.plot(test_df['date'], test_df['revenue'])
plt.title('Test Plot - Should Appear Inline')
plt.show()

print("✓ If you see a plot above, Cursor inline visualization works!")