A complete, production-ready AI & ML platform for automateddata visualization, prediction, and PDF reporting.Developed by Aluvala Ediga Harsha Vardhan Goud (MCA)
DataSci is an intelligent AI-based data analysis system that enables anyone to upload a CSV file and instantly receive:
-
Cleaned and analyzed data
-
Automated visualizations
-
Machine learning predictions
-
Accuracy / R² score evaluation
-
Printable PDF reports
-
Firebase-secured user profiles
-
Cloud-hosted, polished web interface
-
Email/password authentication
-
Firestore user profile storage
-
Cloud-safe session handling
-
Auto-detect encoding
-
Auto-fix missing values
-
Auto-convert numeric columns
-
Preview first 20 rows
Supported Chart Types:
-
Scatter — Compare numeric relationships
-
Line — Trend and time-series analysis
-
Bar — Category comparison
-
Histogram — Distribution patterns
-
Heatmap — Correlation matrix
-
Linear Regression
-
Decision Tree Regression
-
Random Forest Regression
-
KNN Regression
-
Support Vector Regression (SVR)
-
Logistic Regression
-
Decision Tree Classifier
-
Random Forest Classifier
-
KNN Classifier
-
Support Vector Machine (SVM)
-
KMeans (3 clusters)
-
KMeans (5 clusters)
-
Train/Test split
-
StandardScaler normalization
-
Label encoding
-
Automated prediction output
-
Visualization report
-
Prediction metrics report
-
Branded header & footer
-
Embedded PNG charts
-
Clean tabular formatting
-
HTML5
-
CSS
-
Bootstrap
-
Jinja2
-
Plotly.js
-
Python 3.11
-
Flask
-
Pandas
-
NumPy
-
Scikit-Learn
-
ReportLab
-
Firebase Authentication
-
Firebase Firestore
-
Render (Deployment)
Click to Expand
{
"FIREBASE_WEB_CONFIG": "{...}",
"FIREBASE_ADMIN_JSON": "{...}",
"FLASK_SECRET": "your-secret-key",
"PORT": "5000"
}-
Industry-ready architecture (Firebase + Render + Python ML)
-
Full-stack + AI skillset (Auth, Backend, ML, UI, PDF)
-
Real-time predictions with accuracy and R² score
-
Branded auto-generated PDF reports
-
Strong deployment & cloud integration
-
Free tier offers only 512 MB RAM
-
Heavy models (Random Forest, SVM, KMeans) may cause slowdowns
-
Large CSVs may trigger temporary app restarts
-
This is due to cloud limitations, not backend issues
-
Recommended: use smaller datasets or upgrade plan
🔗 Render Deployment:
Aluvala Ediga Harsha Vardhan GoudMCA — AI & ML Developer
Click to Expand
git clone https://github.com/Aluval/DataSci.git
cd DataSci
pip install -r requirements.txt
python app.pyMIT LicenseDo not sell commercially without permission.
If you found this project useful:
-
Star ⭐ the repo
-
Share it
-
Help more developers discover it