🚀 Transform your CSV data into professional, interactive dashboards with intelligent chart selection, AI-powered insights, and beautiful themes - all in seconds, with zero configuration required!

💬 You: "What's the highest expense and when did it occur?"
🤖 AI: "The highest expense was $215,000 which occurred on 2024-01-25"

💬 You: "Show me sales trends by region"  
🤖 AI: "North America leads with $67,440 total revenue, showing 15.2% growth"

1. ✅ Select Columns - Choose data with intuitive checkboxes
2. 🔍 Get AI Suggestions - Intelligent chart recommendations
3. 🎨 Pick Your Favorites - Multiple chart types available
4. 📊 Show Charts - Beautiful visualizations in seconds!

• 🎨 Plotly - Clean and modern
• ⚪ Plotly White - Minimalist elegance
• 🌙 Plotly Dark - Sleek dark mode
• 📊 GGPlot2 - Statistical styling
• 🌊 Seaborn - Data science favorite
• 🤍 Simple White - Pure simplicity

# The AI decides what charts to create:
Time Series Data → Line charts, area charts, trend analysis
Categorical Data → Bar charts, pie charts, donut charts
Geographic Data → Maps, heatmaps, choropleth
Correlation Data → Scatter plots, correlation matrices
Distribution Data → Histograms, box plots, violin plots
Comparison Data → Bar charts, radar charts, parallel coordinates
Part-to-Whole → Pie charts, treemaps, stacked bars
Ranking Data → Horizontal bars, lollipop charts

• Python 3.8 or higher
• pip package manager

1. Clone the Repository

   git clone https://github.com/yourusername/ChartCraft-AI.git
   cd ChartCraft-AI

2. Create Virtual Environment

   python -m venv venv
   
   # Windows
   venv\Scripts\activate
   
   # macOS/Linux
   source venv/bin/activate

3. Install Dependencies

   pip install -r requirements.txt

4. Run the Application

   streamlit run app.py

5. Open in Browser

   • The app will automatically open at http://localhost:8501
   • If not, navigate to the URL shown in the terminal

# Create conda environment
conda create -n chartcraft python=3.8
conda activate chartcraft

# Install dependencies
pip install -r requirements.txt

# Run application
streamlit run app.py

• Drag and drop your CSV file into the upload area
• Or click "Browse files" to select your CSV
• The app automatically detects column types and data patterns

• View automatically generated visualizations in the "Dashboard" tab
• Charts are intelligently selected based on your data characteristics
• Key metrics are displayed at the top of the dashboard

• Use the sidebar filters to focus on specific data subsets
• Numeric filters: Range sliders for continuous variables
• Categorical filters: Multi-select dropdowns for categories
• Charts update automatically when filters are applied

• Choose different themes from the sidebar
• Override automatic chart selection with manual choices
• Use the "Generate Smart Charts" button to refresh visualizations

• Visit the "Insights" tab for AI-powered data analysis
• Get automated observations about data quality, patterns, and recommendations
• Understand your data story through natural language explanations

• Charts: Export as PNG ZIP or comprehensive PDF reports
• Data: Download filtered data as CSV or Excel with multiple sheets
• Reports: Generate professional reports with charts and insights

ChartCraftAI/
├── app.py                 # Main Streamlit application
├── data_analyzer.py       # Intelligent data analysis engine
├── chart_selector.py      # Smart chart selection algorithm
├── insights_generator.py  # AI-powered insights generation
├── export_handler.py      # Multi-format export functionality
└── requirements.txt       # Python dependencies

1. DataAnalyzer: Intelligent data type detection, pattern recognition, quality assessment
2. ChartSelector: Algorithm for optimal chart selection based on data characteristics
3. InsightsGenerator: AI-powered analysis for business intelligence and recommendations
4. ExportHandler: Multi-format export capabilities (PNG, PDF, Excel, CSV)

# In chart_selector.py, add your custom chart method
def _create_custom_chart(self, theme: str) -> List[Dict[str, Any]]:
    # Your custom visualization logic
    pass

# Register in generate_smart_charts method
charts.extend(self._create_custom_chart(theme))

# Add new themes to the theme selector in app.py
available_themes = [
    "plotly", "plotly_white", "plotly_dark", 
    "ggplot2", "seaborn", "simple_white",
    "your_custom_theme"  # Add here
]

# In insights_generator.py, add new insight methods
def _generate_custom_insights(self):
    insights = []
    # Your custom insight logic
    self.insights.append({
        'category': '🔥 Custom Analysis',
        'points': insights
    })

date,revenue,product,region,sales_rep
2024-01-01,15000,Product A,North,John
2024-01-02,12000,Product B,South,Jane

Auto-Generated Charts: Time series revenue, product comparison, regional analysis

age,satisfaction,category,purchase_intent,location
25,4,Premium,Yes,Urban
34,3,Standard,No,Suburban

Auto-Generated Charts: Satisfaction distribution, age demographics, intent analysis

campaign,impressions,clicks,conversions,cost,channel
Campaign A,10000,500,50,1000,Google
Campaign B,8000,400,60,800,Facebook

Auto-Generated Charts: ROI analysis, channel comparison, funnel visualization

1. Installation Problems

# If you get permission errors
pip install --user -r requirements.txt

# If specific packages fail
pip install streamlit plotly pandas numpy matplotlib seaborn

2. Memory Issues with Large Files

• Files >100MB may cause performance issues
• Consider sampling your data for exploration
• Use filters to reduce data size for analysis

3. Chart Generation Failures

• Check for special characters in column names
• Ensure data types are consistent
• Remove completely empty columns

4. Export Issues

# Install additional dependencies for PDF export
pip install reportlab python-pptx kaleido

# For geographic visualizations
pip install folium geopandas

• Large Datasets: Use sampling or filtering for datasets >50,000 rows
• Many Columns: Focus analysis on most relevant columns
• Memory Usage: Close browser tabs and restart Streamlit if memory issues occur

This project is licensed under the MIT License - see the LICENSE file for details.