CoolFace
Apppublic

flexfitfury9/Ai-Data-Analysis-Tool

sourceHugging Faceupdated 9mo agoView on Hugging Face
0likes
App README

Data Analysis Engine

A comprehensive data analysis dashboard built with Streamlit that transforms raw CSV data into actionable insights and visualizations.

Features

  • —Data Loading: Upload and preview CSV files with automatic dataset overview
  • —Data Cleaning: Handle missing values, remove duplicates, and preprocess data
  • —Statistical Analysis: Generate descriptive statistics, correlation analysis, and trend detection
  • —Interactive Visualizations: Create various chart types including histograms, scatter plots, line charts, bar charts, box plots, and heatmaps
  • —User-Friendly Interface: Intuitive navigation with a clean, modern design

How It Works

  1. 1.Load messy data: Upload your raw CSV file using the file uploader
  2. 2.Clean missing values: Use the data cleaning tools to handle missing values and preprocess your data
  3. 3.Detect trends and patterns: Analyze correlations, statistical summaries, and trends in your data
  4. 4.Visualize results: Create interactive charts and graphs to understand your data

Requirements

  • —Python 3.7+
  • —Streamlit
  • —Pandas
  • —NumPy
  • —Matplotlib
  • —Seaborn
  • —Plotly
  • —Scikit-learn

Installation

  1. 1.Clone or download this repository
  2. 2.Install the required dependencies:
   pip install -r requirements.txt
  1. 1.Run the Streamlit application:
   streamlit run streamlit_data_analyzer.py

Usage

  1. 1.Navigate to the "Data Upload" section to upload your CSV file
  2. 2.Go to "Data Cleaning" to preprocess and clean your data
  3. 3.Use "Analysis & Insights" to discover patterns and statistical relationships
  4. 4.Visit "Visualization" to create charts and graphs for your data

Sample Data

The repository includes a sample_data.csv file with employee information that you can use to test the application.

Technologies Used

  • —Streamlit: For the web-based dashboard interface
  • —Pandas: For data manipulation and analysis
  • —Plotly: For interactive visualizations
  • —Scikit-learn: For advanced statistical analysis
  • —Matplotlib/Seaborn: For additional visualization options