Metadata-Version: 2.4
Name: dive-for-data
Version: 0.1.0
Summary: Data Insight and Visualization Engine
Author-email: argon2019pleaseplease <pleasework413@gmail.com>
License: GPL-3.0-only
Project-URL: Homepage, https://github.com/sir-cakes-alot/dive
Keywords: data,statistics,visualization,prediction
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
Classifier: Operating System :: OS Independent
Classifier: Intended Audience :: Developers
Classifier: Topic :: Scientific/Engineering :: Information Analysis
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Dynamic: license-file

# dive
DIVE — Data Insights & Visualization Experience

`dive/main.py` implements `Dive`, a small pure-Python container for ordered numeric data with:
- statistical summaries (`mean`, `median`, `mode`, `stdev`, `variance`, `skewness`, `kurtosis`, etc.)
- quantiles and histograms (`percentile`, `quartiles`, `iqr`)
- data transforms (`z_scores`, `normalized`, `cumulative_sum`, `moving_average`, `diff`, `pct_change`, `sorted`, `clip`, `apply`)
- prediction engine (`predict_next`, `predict_detail`, `linear`, `quadratic`, `holt`, `exponential`, `drift`, `newton`, `lagrange`, `seasonal`, `ensemble`)
- regression/correlation analysis (`correlation`, `covariance`, `regress_on`)
- ASCII visualizations (`histogram`, `sparkline`, `plot_ascii`)
- utility exports (`to_list`, `to_dict`)

---

## Installation

No packaging yet; use directly from source:

```bash
git clone <repo>
cd dive
python -m pip install .    # (optional if configured as package)
```

## Quickstart

```python
from main import Dive

# create dataset
sales = Dive([100, 150, 120, 200, 180])
print(sales.mean())          # 150.0
print(sales.summary())

# add new value
sales += 220
print(sales[-1])            # 220

# predict next value (ensemble model)
print(sales.predict_next())

# use reference series for regression mode (len(reference)==len(self)+steps)
temps = Dive([20, 25, 22, 30, 28, 35])
print(sales.predict_next(reference=temps, TA=1))

# detailed prediction report
print(sales.predict_detail(steps=3, reference=temps, TA=1))
``` 

## API overview

### Data management
- `Dive(data=None)`
- `add`, `append`, `remove`, `pop`, `clear`, `copy`, `data` property
- supports Python protocols: `len`, indexing, iteration, `in`, equality

### Stats
- `mean`, `median`, `mode`, `geo_mean`, `harmonic_mean`
- `stdev`, `variance`, `range`, `min`, `max`, `sum`
- `percentile`, `quartiles`, `iqr`.

### Prediction
- `predict_next(steps=1, method='ensemble', reference=None, corr_threshold=0.1, TA=0)`
- `predict_detail(...)`

### Cross-dataset
- `correlation(other)`
- `covariance(other)`
- `regress_on(other)`

### Visualization
- `summary()` / `describe()`
- `histogram(bins=10, width=40)`
- `sparkline()`
- `plot_ascii(width=60, height=15)`

## Notes

`main.py` includes a built-in quick test in `if __name__ == '__main__'` that evaluates prediction accuracy over polynomial and series models.

To see the full behavior, run:

```bash
python main.py
```

