Metadata-Version: 2.4
Name: panadaspy
Version: 0.1.0
Summary: A Python package to quickly access Computer Laboratory - II (BE AI&DS) Bioinformatics and Information Retrieval practical codes, theory, experiment mappings, and automated datasets
Author: Ayyub
License: MIT
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Topic :: Education
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
Classifier: Topic :: Scientific/Engineering :: Information Analysis
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.7
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: pandas
Requires-Dist: numpy
Requires-Dist: scikit-learn
Requires-Dist: matplotlib
Requires-Dist: seaborn
Requires-Dist: scipy
Requires-Dist: nltk
Requires-Dist: requests
Dynamic: license-file

# panadaspy 🚀

A Python package to quickly access **Computer Laboratory - II (BE AI&DS)** practical source codes, theoretical background, experiment aim mappings, and automatically bundled datasets covering **Bioinformatics (BI)** and **Information Retrieval (IR)**.

---

## 📦 Installation

Once published to PyPI, you can install the package on any machine using:

```bash
pip install panadaspy
```

To install locally in editable mode (development):

```bash
cd panadaspy
pip install -e .
```

---

## ⚡ Quickstart

```python
import panadaspy as pdp

# 1. Print all experiments, aims, domains, and dataset mappings
pdp.print_mapping()
# or
pdp.list_experiments()

# 2. Print source code for Practical 1 (DNA Sequence Analysis)
pdp.print_practical(1)

# 3. Print code using domain prefixes ('BI1'..'BI6' or 'IR1'..'IR5')
pdp.print_practical("BI1")  # DNA Sequence Analysis
pdp.print_practical("IR3")  # Bayesian Network Medical Diagnosis (extracts processed.cleveland.data)

# 4. Print all Bioinformatics or all Information Retrieval practicals
pdp.print_practical("BI")   # Displays Practicals 1 to 6
pdp.print_practical("IR")   # Displays Practicals 7 to 11

# 5. Print comprehensive theory, math formulas, and concepts
pdp.print_theory(9)         # Bayesian Network math & Bayes' rule
pdp.print_theory("BI2")     # RNA-Seq Log2FC & Benjamini-Hochberg FDR theory

# 6. Extract datasets manually into the current working directory
pdp.download_dataset(9)     # Extracts processed.cleveland.data
pdp.download_all_datasets() # Extracts all bundled datasets

# 7. Execute a practical in a clean namespace
pdp.run_practical(11)       # Runs PageRank algorithm directly
```

---

## 📋 Available Practicals & Aim Mappings

### 🧬 Part I: Bioinformatics (BI)

| Exp # | Domain Key | Experiment Title | Aim & Focus | Datasets |
|:---:|:---:|---|---|---|
| **1** | `BI1` | **DNA Sequence Analysis** | Nucleotide validation, GC content calculation, motif pattern search, and 3-frame Open Reading Frame (ORF) extraction | *In-memory / Interactive* |
| **2** | `BI2` | **RNA-Seq Data Analysis & Differential Gene Expression** | Log2 Fold Change, Student's t-test, Benjamini-Hochberg FDR correction, Volcano Plot, and CSV export | `differential_expression_results.csv` |
| **3** | `BI3` | **Protein Secondary Structure Prediction & Homology Alignment** | 20-amino acid validation, pairwise template alignment, sequence identity %, modeling confidence, and secondary structure | *In-memory / Interactive* |
| **4** | `BI4` | **Molecular Docking & Virtual Screening** | Ligand SMILES descriptors, Lipinski's Rule of 5 filter, descriptor distance ranking, and AutoDock Vina 3D grid setup | *In-memory / Descriptors* |
| **5** | `BI5` | **Machine Learning in Bioinformatics** | SNP genomic classification comparing SVM (RBF kernel) vs Random Forest, Confusion Matrix, and top 15 marker ranking | *Synthetic Genomic Data* |
| **6** | `BI6` | **Crop Marker-Trait Association & Yield Prediction** | Pearson correlation screening, Random Forest continuous yield regression (MAE, RMSE, $R^2$), and genomic selection | *Crop Genomic Data* |

### 🔍 Part II: Information Retrieval (IR)

| Exp # | Domain Key | Experiment Title | Aim & Focus | Datasets |
|:---:|:---:|---|---|---|
| **7** | `IR1` | **Text Preprocessing for Information Retrieval** | Tokenization, case folding, stop word removal, and Porter Stemmer morphological reduction using NLTK | *Sample Text Corpus* |
| **8** | `IR2` | **Document Retrieval using Inverted Index & Boolean Model** | Inverted index data structure construction and multi-term conjunctive Boolean retrieval via postings intersection | *Document Collection* |
| **9** | `IR3` | **Bayesian Network for Medical Diagnosis** | Cleveland Heart Disease dataset, clinical attribute discretization, prior & conditional probabilities, and Bayes' diagnosis | `processed.cleveland.data` |
| **10** | `IR4` | **Agglomerative Hierarchical Clustering** | StandardScaler normalization, Ward linkage Dendrogram, Agglomerative Clustering ($K=3$), and 2D cluster scatter plot | `iris.csv` |
| **11** | `IR5` | **PageRank Algorithm Implementation** | Directed web graph modeling, Random Surfer Model with damping factor ($d=0.85$), and iterative power method | *Directed Web Graph* |

---

## 🌟 Key Features

- **Instant Source Code Access**: View clean, ready-to-run source code for every practical.
- **Dual Identification System**: Access practicals seamlessly using numeric IDs (`1` to `11`) or domain keys (`BI1` to `BI6`, `IR1` to `IR5`).
- **Group Inspections**: Inspect all Bioinformatics practicals at once with `pdp.print_practical('BI')` or all IR practicals with `pdp.print_practical('IR')`.
- **Automated Offline Datasets**: Pre-bundled datasets (`differential_expression_results.csv`, `processed.cleveland.data`, `iris.csv`) automatically extract to your current working directory when needed without internet access.
- **Detailed Theory & Mathematical Formulations**: Deep-dive into Bayes' theorem, Lipinski's Rule of 5, Benjamini-Hochberg FDR correction, Ward's hierarchical variance, and PageRank power iteration using `pdp.print_theory(n)`.
- **Direct Execution**: Run practicals directly from Python with `pdp.run_practical(n)`.

---

## 📄 License

MIT License. Copyright (c) 2026 Ayyub.
