# AskPandas: AI-Powered Data Engineering & Analytics Assistant
[](https://www.python.org/downloads/)
[](https://opensource.org/licenses/MIT)
[](https://badge.fury.io/py/askpandas)
[](https://pepy.tech/project/askpandas)
[](https://github.com/irfanalidv/AskPandas)
[](https://github.com/irfanalidv/AskPandas)
[](https://github.com/irfanalidv/AskPandas/issues)
AskPandas is an open-source Python library that lets you query and transform CSV data using natural language, powered by free, local open-source LLMs via Ollama. **No API keys, no cloud, no cost.**
## 🚀 **Quick Start (5 minutes!)**
### 1. **Install AskPandas**
```bash
pip install askpandas
```
### 2. **Install Ollama (one command)**
```bash
# macOS/Linux
curl -fsSL https://ollama.com/install.sh | sh
# Windows: Download from https://ollama.com/download
```
### 3. **Pull a lightweight model**
```bash
ollama pull phi3:mini # Very small, very fast
```
### 4. **Start Ollama**
```bash
ollama serve
```
### 5. **Start analyzing data!**
```python
import askpandas as ap
# Set up AI
llm = ap.OllamaLLM(model_name="phi3:mini")
ap.set_llm(llm)
# Load your data
df = ap.DataFrame("your_data.csv")
# Ask questions in plain English!
result = df.chat("What is the total revenue?")
print(result)
```
### 🚀 **See It In Action!**
```python
import askpandas as ap
import pandas as pd
# Create sample data
data = {
'product': ['Apple', 'Banana', 'Orange'],
'price': [2.50, 1.00, 1.50],
'quantity': [100, 200, 150]
}
df = pd.DataFrame(data)
df['revenue'] = df['price'] * df['quantity']
# Create AskPandas DataFrame
sales_df = ap.DataFrame(df)
# AI-powered analysis
result = sales_df.chat("What is the total revenue?")
# Output: Total Revenue: $675.00
# More complex queries
result = sales_df.chat("Show me the top 3 products by revenue")
# Output: Product analysis with rankings
result = sales_df.chat("Calculate average price by product")
# Output: Average Price: $1.67
```
## 🎯 **What Can You Do? (Everything!)**
### 📊 **Data Analysis - Just Ask!**
```python
# Basic questions
df.chat("What is the average price?")
# Output: Average Price: $1.67
df.chat("Show me the top 5 customers by revenue")
# Output: Customer rankings with revenue amounts
df.chat("How many sales were made in each region?")
# Output: Regional sales breakdown
# Complex analysis
df.chat("""
Analyze our sales performance:
1. Calculate total revenue by month
2. Show the trend over time
3. Identify the best performing products
4. Create a visualization
""")
# Output: Comprehensive analysis with insights
```
### 🎨 **Beautiful Visualizations - Automatically!**
```python
# Charts are created automatically
df.chat("Create a bar chart of sales by region")
df.chat("Plot revenue trends over time")
df.chat("Show correlation between price and quantity")
df.chat("Display distribution of customer ages")
```
### 🔍 **Data Quality & Cleaning**
```python
# Automatic data assessment
df.chat("Check for missing values and duplicates")
df.chat("Identify outliers in numeric columns")
df.chat("Clean column names and standardize formats")
df.chat("Validate data types and suggest improvements")
```
### 🌐 **Multi-Dataset Analysis**
```python
# Work with multiple files
customers = ap.DataFrame("customers.csv")
orders = ap.DataFrame("orders.csv")
products = ap.DataFrame("products.csv")
# Cross-dataset insights
ap.chat("""
Customer analysis:
1. Join customers with their orders
2. Calculate lifetime value by segment
3. Show purchase patterns
4. Identify high-value customers
""", customers, orders, products)
```
## 💡 **Real-World Examples**
### 📈 **Sales Analysis**
```python
import askpandas as ap
# Load sales data
sales = ap.DataFrame("sales_data.csv")
# Comprehensive sales report
sales.chat("What is our total revenue?")
# Output: Total Revenue: $78,586.11
sales.chat("Show me the top 3 products by revenue")
# Output: Product rankings with revenue amounts
sales.chat("Calculate average order value by region")
# Output: Regional performance metrics
sales.chat("How many sales were made in each region?")
# Output: Regional sales breakdown
```
### 👥 **Customer Analytics**
```python
# Customer behavior analysis
customers = ap.DataFrame("customers.csv")
transactions = ap.DataFrame("transactions.csv")
ap.chat("""
Customer behavior insights:
1. Customer lifetime value analysis
2. Purchase frequency patterns
3. Churn prediction factors
4. Customer satisfaction metrics
5. Personalized marketing recommendations
""", customers, transactions)
```
### 📊 **Financial Analysis**
```python
# Financial data processing
financial = ap.DataFrame("financial_data.csv")
financial.chat("""
Financial performance review:
1. Profit and loss analysis
2. Cash flow trends
3. Expense categorization
4. Budget vs actual comparison
5. Financial ratios and KPIs
6. Risk assessment and recommendations
""")
```
### 🔬 **Research & Academic**
```python
# Research data analysis
research = ap.DataFrame("research_data.csv")
research.chat("""
Statistical analysis:
1. Descriptive statistics for all variables
2. Correlation analysis between key factors
3. Hypothesis testing results
4. Outlier detection and treatment
5. Data distribution visualizations
6. Statistical significance testing
""")
```
## 🛠️ **Advanced Features**
### 🔧 **Custom Configuration**
```python
import askpandas as ap
# Set your preferences
ap.set_config(
verbose=True, # See what's happening
plot_style="seaborn", # Beautiful charts
output_dir="my_analysis", # Save results here
max_execution_time=120, # Allow longer analysis
enable_history=True # Track all queries
)
```
### 🎨 **Custom Visualizations**
```python
# Create custom charts
from askpandas.visualization.charts import create_bar_chart, save_plot
# Custom bar chart
fig = create_bar_chart(
df.df,
x_col="category",
y_col="value",
title="My Custom Chart",
figsize=(12, 8)
)
# Save with high quality
save_plot(fig, "custom_chart.png", dpi=300)
```
### 🔍 **Query Intelligence**
```python
# Get help with your queries
query = "Show me sales trends"
analysis = ap.analyze_query(query)
print(f"Query type: {analysis['primary_category']}")
# Get suggestions
suggestions = ap.get_query_examples('visualization')
print("Try these:", suggestions[:3])
# Validate your query
validation = ap.validate_query(query, df.columns)
if validation['is_valid']:
print("✅ Query is valid!")
```
## 🚀 **Performance Tips for Best Results**
### 💪 **Optimize Your Queries**
```python
# ✅ Good - Specific and clear
df.chat("Calculate total revenue by month for 2024, excluding returns")
# ❌ Avoid - Too vague
df.chat("Analyze this data")
# ✅ Good - Step-by-step analysis
df.chat("""
1. Filter data for Q4 2024
2. Group by product category
3. Calculate sum of revenue
4. Sort by revenue descending
5. Show top 10 results
""")
# ✅ Good - Include context
df.chat("Show customer retention rate, considering customers who made purchases in both 2023 and 2024")
```
### 🎯 **Choose the Right Model**
```python
# For speed and basic analysis
llm = ap.OllamaLLM(model_name="phi3:mini") # Fastest
# For better quality and complex queries
llm = ap.OllamaLLM(model_name="mistral:7b") # Balanced
# For best results (slower)
llm = ap.OllamaLLM(model_name="llama3.2:13b") # Highest quality
```
### 📊 **Data Preparation Tips**
```python
# Clean your data first
df = ap.DataFrame("messy_data.csv")
# Ask AskPandas to help clean it
df.chat("""
Help me clean this data:
1. Identify and handle missing values
2. Remove duplicates
3. Fix data type issues
4. Standardize column names
5. Show me what was cleaned
""")
# Then analyze the clean data
df.chat("Now analyze the cleaned data for insights")
```
## 🔧 **Installation Options**
### **Basic Installation**
```bash
pip install askpandas
```
### **Full Installation (Recommended)**
```bash
pip install "askpandas[full]"
```
### **Development Installation**
```bash
git clone https://github.com/irfanalidv/AskPandas
cd AskPandas
pip install -e ".[dev]"
```
## 📱 **Platform Support**
- ✅ **macOS** - Native support with Apple Silicon optimization
- ✅ **Linux** - Full compatibility with all distributions
- ✅ **Windows** - Complete support with WSL2 recommended
- ✅ **Cloud** - Works on Google Colab, AWS, Azure, etc.
## 🆘 **Troubleshooting**
### **Common Issues & Solutions**
**"No LLM configured" error?**
```bash
# Make sure Ollama is running
ollama serve
# Check if model is downloaded
ollama list
```
**Slow responses?**
```bash
# Try a smaller model
ollama pull phi3:mini
# Close other applications to free memory
```
**Installation issues?**
```bash
# Update pip
pip install --upgrade pip
# Install with specific Python version
python3.9 -m pip install askpandas
```
## 📚 **Learning Resources**
### **Interactive Examples**
```bash
# Run the interactive demo
python simple_demo.py
# Try the configuration setup
python simple_config.py
```
### **Sample Datasets**
- `fake_sample.csv` - Small sample for testing
- `comprehensive_sample.csv` - Larger dataset for practice
- Create your own CSV files and start analyzing!
## 🎉 **Success Stories**
### **Data Scientists**
> "AskPandas reduced my data exploration time from hours to minutes. I can now focus on insights instead of coding."
### **Business Analysts**
> "I can analyze complex datasets without learning Python syntax. Natural language queries are a game-changer!"
### **Researchers**
> "Perfect for exploratory data analysis. I can quickly test hypotheses and generate visualizations for papers."
### **Students**
> "Learning data analysis has never been easier. AskPandas makes complex concepts accessible."
## 🚀 **What's Next?**
### **Version 0.2.0 (Coming Soon)**
- [ ] Jupyter notebook integration
- [ ] More visualization options (Plotly, Bokeh)
- [ ] SQL query generation
- [ ] Data pipeline automation
### **Version 1.0.0 (Future)**
- [ ] Enterprise features
- [ ] Advanced ML integration
- [ ] Real-time data streaming
- [ ] Community plugins
## 🤝 **Get Help & Contribute**
- **📖 Documentation**: [GitHub Wiki](https://github.com/irfanalidv/AskPandas/wiki)
- **🐛 Bug Reports**: [GitHub Issues](https://github.com/irfanalidv/AskPandas/issues)
- **💬 Discussions**: [GitHub Discussions](https://github.com/irfanalidv/AskPandas/discussions)
- **⭐ Star**: [GitHub Repository](https://github.com/irfanalidv/AskPandas)
## 📄 **License**
MIT License - Use freely for personal and commercial projects!
## 🙏 **Acknowledgments**
- **Ollama Team** - Making local AI accessible
- **HuggingFace** - Open-source AI models
- **Pandas Community** - Amazing data tools
- **Open Source Contributors** - Building the future together
## 🎯 **Complete Working Demonstration**
Want to see everything in action? Run our comprehensive demo:
```bash
# Clone the repository
git clone https://github.com/irfanalidv/AskPandas.git
cd AskPandas
# Run the complete demonstration
python final_working_demo.py
```
This demo showcases:
- ✅ **DataFrame Creation & Analysis** - Real data processing
- ✅ **Data Quality & Cleaning** - Automatic column standardization
- ✅ **AI-Powered Queries** - Natural language analysis
- ✅ **Multi-Dataset Analysis** - Joining and complex queries
- ✅ **Configuration Management** - Customizable settings
- ✅ **Query Intelligence** - Automatic query categorization
### **🚀 Quick Test**
```python
import askpandas as ap
import pandas as pd
# Create test data
data = {'name': ['Alice', 'Bob'], 'age': [25, 30], 'salary': [50000, 60000]}
df = pd.DataFrame(data)
ap_df = ap.DataFrame(df)
# Test basic methods
print(f"Shape: {ap_df.shape()}") # Output: Shape: (2, 3)
print(f"Columns: {ap_df.columns()}") # Output: Columns: ['name', 'age', 'salary']
# Get comprehensive info
print(ap_df.info()) # Output: Detailed DataFrame information
# Statistical description
print(ap_df.describe()) # Output: Statistical summary
```
---
**🚀 Ready to transform your data analysis? Install AskPandas today!**
```bash
pip install askpandas
```
**Made with ❤️ by Md Irfan Ali**
Raw data
{
"_id": null,
"home_page": "https://github.com/irfanalidv/AskPandas",
"name": "askpandas",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "data-analysis, pandas, ai, natural-language, csv, data-science, machine-learning, llm, ollama, huggingface",
"author": "Md Irfan Ali",
"author_email": "irfanali29@hotmail.com",
"download_url": "https://files.pythonhosted.org/packages/67/43/dbe230f54f55fc48f929e96f56df8a28677d0ffd6eb28ec2c5860af86a6e/askpandas-0.1.1.tar.gz",
"platform": null,
"description": "# AskPandas: AI-Powered Data Engineering & Analytics Assistant\n\n[](https://www.python.org/downloads/)\n[](https://opensource.org/licenses/MIT)\n[](https://badge.fury.io/py/askpandas)\n[](https://pepy.tech/project/askpandas)\n[](https://github.com/irfanalidv/AskPandas)\n[](https://github.com/irfanalidv/AskPandas)\n[](https://github.com/irfanalidv/AskPandas/issues)\n\nAskPandas is an open-source Python library that lets you query and transform CSV data using natural language, powered by free, local open-source LLMs via Ollama. **No API keys, no cloud, no cost.**\n\n## \ud83d\ude80 **Quick Start (5 minutes!)**\n\n### 1. **Install AskPandas**\n\n```bash\npip install askpandas\n```\n\n### 2. **Install Ollama (one command)**\n\n```bash\n# macOS/Linux\ncurl -fsSL https://ollama.com/install.sh | sh\n\n# Windows: Download from https://ollama.com/download\n```\n\n### 3. **Pull a lightweight model**\n\n```bash\nollama pull phi3:mini # Very small, very fast\n```\n\n### 4. **Start Ollama**\n\n```bash\nollama serve\n```\n\n### 5. **Start analyzing data!**\n\n```python\nimport askpandas as ap\n\n# Set up AI\nllm = ap.OllamaLLM(model_name=\"phi3:mini\")\nap.set_llm(llm)\n\n# Load your data\ndf = ap.DataFrame(\"your_data.csv\")\n\n# Ask questions in plain English!\nresult = df.chat(\"What is the total revenue?\")\nprint(result)\n```\n\n### \ud83d\ude80 **See It In Action!**\n\n```python\nimport askpandas as ap\nimport pandas as pd\n\n# Create sample data\ndata = {\n 'product': ['Apple', 'Banana', 'Orange'],\n 'price': [2.50, 1.00, 1.50],\n 'quantity': [100, 200, 150]\n}\ndf = pd.DataFrame(data)\ndf['revenue'] = df['price'] * df['quantity']\n\n# Create AskPandas DataFrame\nsales_df = ap.DataFrame(df)\n\n# AI-powered analysis\nresult = sales_df.chat(\"What is the total revenue?\")\n# Output: Total Revenue: $675.00\n\n# More complex queries\nresult = sales_df.chat(\"Show me the top 3 products by revenue\")\n# Output: Product analysis with rankings\n\nresult = sales_df.chat(\"Calculate average price by product\")\n# Output: Average Price: $1.67\n```\n\n## \ud83c\udfaf **What Can You Do? (Everything!)**\n\n### \ud83d\udcca **Data Analysis - Just Ask!**\n\n```python\n# Basic questions\ndf.chat(\"What is the average price?\")\n# Output: Average Price: $1.67\n\ndf.chat(\"Show me the top 5 customers by revenue\")\n# Output: Customer rankings with revenue amounts\n\ndf.chat(\"How many sales were made in each region?\")\n# Output: Regional sales breakdown\n\n# Complex analysis\ndf.chat(\"\"\"\n Analyze our sales performance:\n 1. Calculate total revenue by month\n 2. Show the trend over time\n 3. Identify the best performing products\n 4. Create a visualization\n\"\"\")\n# Output: Comprehensive analysis with insights\n```\n\n### \ud83c\udfa8 **Beautiful Visualizations - Automatically!**\n\n```python\n# Charts are created automatically\ndf.chat(\"Create a bar chart of sales by region\")\ndf.chat(\"Plot revenue trends over time\")\ndf.chat(\"Show correlation between price and quantity\")\ndf.chat(\"Display distribution of customer ages\")\n```\n\n### \ud83d\udd0d **Data Quality & Cleaning**\n\n```python\n# Automatic data assessment\ndf.chat(\"Check for missing values and duplicates\")\ndf.chat(\"Identify outliers in numeric columns\")\ndf.chat(\"Clean column names and standardize formats\")\ndf.chat(\"Validate data types and suggest improvements\")\n```\n\n### \ud83c\udf10 **Multi-Dataset Analysis**\n\n```python\n# Work with multiple files\ncustomers = ap.DataFrame(\"customers.csv\")\norders = ap.DataFrame(\"orders.csv\")\nproducts = ap.DataFrame(\"products.csv\")\n\n# Cross-dataset insights\nap.chat(\"\"\"\n Customer analysis:\n 1. Join customers with their orders\n 2. Calculate lifetime value by segment\n 3. Show purchase patterns\n 4. Identify high-value customers\n\"\"\", customers, orders, products)\n```\n\n## \ud83d\udca1 **Real-World Examples**\n\n### \ud83d\udcc8 **Sales Analysis**\n\n```python\nimport askpandas as ap\n\n# Load sales data\nsales = ap.DataFrame(\"sales_data.csv\")\n\n# Comprehensive sales report\nsales.chat(\"What is our total revenue?\")\n# Output: Total Revenue: $78,586.11\n\nsales.chat(\"Show me the top 3 products by revenue\")\n# Output: Product rankings with revenue amounts\n\nsales.chat(\"Calculate average order value by region\")\n# Output: Regional performance metrics\n\nsales.chat(\"How many sales were made in each region?\")\n# Output: Regional sales breakdown\n```\n\n### \ud83d\udc65 **Customer Analytics**\n\n```python\n# Customer behavior analysis\ncustomers = ap.DataFrame(\"customers.csv\")\ntransactions = ap.DataFrame(\"transactions.csv\")\n\nap.chat(\"\"\"\n Customer behavior insights:\n 1. Customer lifetime value analysis\n 2. Purchase frequency patterns\n 3. Churn prediction factors\n 4. Customer satisfaction metrics\n 5. Personalized marketing recommendations\n\"\"\", customers, transactions)\n```\n\n### \ud83d\udcca **Financial Analysis**\n\n```python\n# Financial data processing\nfinancial = ap.DataFrame(\"financial_data.csv\")\n\nfinancial.chat(\"\"\"\n Financial performance review:\n 1. Profit and loss analysis\n 2. Cash flow trends\n 3. Expense categorization\n 4. Budget vs actual comparison\n 5. Financial ratios and KPIs\n 6. Risk assessment and recommendations\n\"\"\")\n```\n\n### \ud83d\udd2c **Research & Academic**\n\n```python\n# Research data analysis\nresearch = ap.DataFrame(\"research_data.csv\")\n\nresearch.chat(\"\"\"\n Statistical analysis:\n 1. Descriptive statistics for all variables\n 2. Correlation analysis between key factors\n 3. Hypothesis testing results\n 4. Outlier detection and treatment\n 5. Data distribution visualizations\n 6. Statistical significance testing\n\"\"\")\n```\n\n## \ud83d\udee0\ufe0f **Advanced Features**\n\n### \ud83d\udd27 **Custom Configuration**\n\n```python\nimport askpandas as ap\n\n# Set your preferences\nap.set_config(\n verbose=True, # See what's happening\n plot_style=\"seaborn\", # Beautiful charts\n output_dir=\"my_analysis\", # Save results here\n max_execution_time=120, # Allow longer analysis\n enable_history=True # Track all queries\n)\n```\n\n### \ud83c\udfa8 **Custom Visualizations**\n\n```python\n# Create custom charts\nfrom askpandas.visualization.charts import create_bar_chart, save_plot\n\n# Custom bar chart\nfig = create_bar_chart(\n df.df,\n x_col=\"category\",\n y_col=\"value\",\n title=\"My Custom Chart\",\n figsize=(12, 8)\n)\n\n# Save with high quality\nsave_plot(fig, \"custom_chart.png\", dpi=300)\n```\n\n### \ud83d\udd0d **Query Intelligence**\n\n```python\n# Get help with your queries\nquery = \"Show me sales trends\"\nanalysis = ap.analyze_query(query)\nprint(f\"Query type: {analysis['primary_category']}\")\n\n# Get suggestions\nsuggestions = ap.get_query_examples('visualization')\nprint(\"Try these:\", suggestions[:3])\n\n# Validate your query\nvalidation = ap.validate_query(query, df.columns)\nif validation['is_valid']:\n print(\"\u2705 Query is valid!\")\n```\n\n## \ud83d\ude80 **Performance Tips for Best Results**\n\n### \ud83d\udcaa **Optimize Your Queries**\n\n```python\n# \u2705 Good - Specific and clear\ndf.chat(\"Calculate total revenue by month for 2024, excluding returns\")\n\n# \u274c Avoid - Too vague\ndf.chat(\"Analyze this data\")\n\n# \u2705 Good - Step-by-step analysis\ndf.chat(\"\"\"\n 1. Filter data for Q4 2024\n 2. Group by product category\n 3. Calculate sum of revenue\n 4. Sort by revenue descending\n 5. Show top 10 results\n\"\"\")\n\n# \u2705 Good - Include context\ndf.chat(\"Show customer retention rate, considering customers who made purchases in both 2023 and 2024\")\n```\n\n### \ud83c\udfaf **Choose the Right Model**\n\n```python\n# For speed and basic analysis\nllm = ap.OllamaLLM(model_name=\"phi3:mini\") # Fastest\n\n# For better quality and complex queries\nllm = ap.OllamaLLM(model_name=\"mistral:7b\") # Balanced\n\n# For best results (slower)\nllm = ap.OllamaLLM(model_name=\"llama3.2:13b\") # Highest quality\n```\n\n### \ud83d\udcca **Data Preparation Tips**\n\n```python\n# Clean your data first\ndf = ap.DataFrame(\"messy_data.csv\")\n\n# Ask AskPandas to help clean it\ndf.chat(\"\"\"\n Help me clean this data:\n 1. Identify and handle missing values\n 2. Remove duplicates\n 3. Fix data type issues\n 4. Standardize column names\n 5. Show me what was cleaned\n\"\"\")\n\n# Then analyze the clean data\ndf.chat(\"Now analyze the cleaned data for insights\")\n```\n\n## \ud83d\udd27 **Installation Options**\n\n### **Basic Installation**\n\n```bash\npip install askpandas\n```\n\n### **Full Installation (Recommended)**\n\n```bash\npip install \"askpandas[full]\"\n```\n\n### **Development Installation**\n\n```bash\ngit clone https://github.com/irfanalidv/AskPandas\ncd AskPandas\npip install -e \".[dev]\"\n```\n\n## \ud83d\udcf1 **Platform Support**\n\n- \u2705 **macOS** - Native support with Apple Silicon optimization\n- \u2705 **Linux** - Full compatibility with all distributions\n- \u2705 **Windows** - Complete support with WSL2 recommended\n- \u2705 **Cloud** - Works on Google Colab, AWS, Azure, etc.\n\n## \ud83c\udd98 **Troubleshooting**\n\n### **Common Issues & Solutions**\n\n**\"No LLM configured\" error?**\n\n```bash\n# Make sure Ollama is running\nollama serve\n\n# Check if model is downloaded\nollama list\n```\n\n**Slow responses?**\n\n```bash\n# Try a smaller model\nollama pull phi3:mini\n\n# Close other applications to free memory\n```\n\n**Installation issues?**\n\n```bash\n# Update pip\npip install --upgrade pip\n\n# Install with specific Python version\npython3.9 -m pip install askpandas\n```\n\n## \ud83d\udcda **Learning Resources**\n\n### **Interactive Examples**\n\n```bash\n# Run the interactive demo\npython simple_demo.py\n\n# Try the configuration setup\npython simple_config.py\n```\n\n### **Sample Datasets**\n\n- `fake_sample.csv` - Small sample for testing\n- `comprehensive_sample.csv` - Larger dataset for practice\n- Create your own CSV files and start analyzing!\n\n## \ud83c\udf89 **Success Stories**\n\n### **Data Scientists**\n\n> \"AskPandas reduced my data exploration time from hours to minutes. I can now focus on insights instead of coding.\"\n\n### **Business Analysts**\n\n> \"I can analyze complex datasets without learning Python syntax. Natural language queries are a game-changer!\"\n\n### **Researchers**\n\n> \"Perfect for exploratory data analysis. I can quickly test hypotheses and generate visualizations for papers.\"\n\n### **Students**\n\n> \"Learning data analysis has never been easier. AskPandas makes complex concepts accessible.\"\n\n## \ud83d\ude80 **What's Next?**\n\n### **Version 0.2.0 (Coming Soon)**\n\n- [ ] Jupyter notebook integration\n- [ ] More visualization options (Plotly, Bokeh)\n- [ ] SQL query generation\n- [ ] Data pipeline automation\n\n### **Version 1.0.0 (Future)**\n\n- [ ] Enterprise features\n- [ ] Advanced ML integration\n- [ ] Real-time data streaming\n- [ ] Community plugins\n\n## \ud83e\udd1d **Get Help & Contribute**\n\n- **\ud83d\udcd6 Documentation**: [GitHub Wiki](https://github.com/irfanalidv/AskPandas/wiki)\n- **\ud83d\udc1b Bug Reports**: [GitHub Issues](https://github.com/irfanalidv/AskPandas/issues)\n- **\ud83d\udcac Discussions**: [GitHub Discussions](https://github.com/irfanalidv/AskPandas/discussions)\n- **\u2b50 Star**: [GitHub Repository](https://github.com/irfanalidv/AskPandas)\n\n## \ud83d\udcc4 **License**\n\nMIT License - Use freely for personal and commercial projects!\n\n## \ud83d\ude4f **Acknowledgments**\n\n- **Ollama Team** - Making local AI accessible\n- **HuggingFace** - Open-source AI models\n- **Pandas Community** - Amazing data tools\n- **Open Source Contributors** - Building the future together\n\n## \ud83c\udfaf **Complete Working Demonstration**\n\nWant to see everything in action? Run our comprehensive demo:\n\n```bash\n# Clone the repository\ngit clone https://github.com/irfanalidv/AskPandas.git\ncd AskPandas\n\n# Run the complete demonstration\npython final_working_demo.py\n```\n\nThis demo showcases:\n\n- \u2705 **DataFrame Creation & Analysis** - Real data processing\n- \u2705 **Data Quality & Cleaning** - Automatic column standardization\n- \u2705 **AI-Powered Queries** - Natural language analysis\n- \u2705 **Multi-Dataset Analysis** - Joining and complex queries\n- \u2705 **Configuration Management** - Customizable settings\n- \u2705 **Query Intelligence** - Automatic query categorization\n\n### **\ud83d\ude80 Quick Test**\n\n```python\nimport askpandas as ap\nimport pandas as pd\n\n# Create test data\ndata = {'name': ['Alice', 'Bob'], 'age': [25, 30], 'salary': [50000, 60000]}\ndf = pd.DataFrame(data)\nap_df = ap.DataFrame(df)\n\n# Test basic methods\nprint(f\"Shape: {ap_df.shape()}\") # Output: Shape: (2, 3)\nprint(f\"Columns: {ap_df.columns()}\") # Output: Columns: ['name', 'age', 'salary']\n\n# Get comprehensive info\nprint(ap_df.info()) # Output: Detailed DataFrame information\n\n# Statistical description\nprint(ap_df.describe()) # Output: Statistical summary\n```\n\n---\n\n**\ud83d\ude80 Ready to transform your data analysis? Install AskPandas today!**\n\n```bash\npip install askpandas\n```\n\n**Made with \u2764\ufe0f by Md Irfan Ali**\n",
"bugtrack_url": null,
"license": null,
"summary": "AI-powered data engineering and analytics assistant for querying CSV data using natural language\u2014locally and intelligently",
"version": "0.1.1",
"project_urls": {
"Bug Reports": "https://github.com/irfanalidv/AskPandas/issues",
"Documentation": "https://github.com/irfanalidv/AskPandas#readme",
"Homepage": "https://github.com/irfanalidv/AskPandas",
"Source": "https://github.com/irfanalidv/AskPandas"
},
"split_keywords": [
"data-analysis",
" pandas",
" ai",
" natural-language",
" csv",
" data-science",
" machine-learning",
" llm",
" ollama",
" huggingface"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "f83e572d27fa76cde079fb52d5fb7168967ee0b534cf50ffa478e16e678a98af",
"md5": "753bc7b0627dda6836d84fb994ac0a25",
"sha256": "e77f2e7c9bd763bcf8d13e7acc3cda2952550495c4e4f6a3f0538de322dbb1ea"
},
"downloads": -1,
"filename": "askpandas-0.1.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "753bc7b0627dda6836d84fb994ac0a25",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 51090,
"upload_time": "2025-08-16T09:06:11",
"upload_time_iso_8601": "2025-08-16T09:06:11.467133Z",
"url": "https://files.pythonhosted.org/packages/f8/3e/572d27fa76cde079fb52d5fb7168967ee0b534cf50ffa478e16e678a98af/askpandas-0.1.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "6743dbe230f54f55fc48f929e96f56df8a28677d0ffd6eb28ec2c5860af86a6e",
"md5": "52e8d8a0653233e36bb3a353ec7ffa14",
"sha256": "9703d3fcb852faec2687ab7a1befa34bca2de5fcd507b31f09c755bbda21b961"
},
"downloads": -1,
"filename": "askpandas-0.1.1.tar.gz",
"has_sig": false,
"md5_digest": "52e8d8a0653233e36bb3a353ec7ffa14",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 54067,
"upload_time": "2025-08-16T09:06:13",
"upload_time_iso_8601": "2025-08-16T09:06:13.561756Z",
"url": "https://files.pythonhosted.org/packages/67/43/dbe230f54f55fc48f929e96f56df8a28677d0ffd6eb28ec2c5860af86a6e/askpandas-0.1.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-16 09:06:13",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "irfanalidv",
"github_project": "AskPandas",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "pandas",
"specs": [
[
">=",
"1.5.0"
]
]
},
{
"name": "numpy",
"specs": [
[
">=",
"1.23.0"
]
]
},
{
"name": "matplotlib",
"specs": [
[
">=",
"3.5.0"
]
]
},
{
"name": "seaborn",
"specs": [
[
">=",
"0.12.0"
]
]
},
{
"name": "requests",
"specs": [
[
">=",
"2.28.0"
]
]
},
{
"name": "transformers",
"specs": [
[
">=",
"4.30.0"
]
]
},
{
"name": "torch",
"specs": [
[
">=",
"2.0.0"
]
]
},
{
"name": "faker",
"specs": [
[
">=",
"18.0.0"
]
]
},
{
"name": "pytest",
"specs": [
[
">=",
"7.0.0"
]
]
},
{
"name": "pytest-cov",
"specs": [
[
">=",
"4.0.0"
]
]
},
{
"name": "scipy",
"specs": [
[
">=",
"1.9.0"
]
]
},
{
"name": "psutil",
"specs": [
[
">=",
"5.8.0"
]
]
}
],
"lcname": "askpandas"
}
JSON
