pvanalytics

What it is and what it does

PVAnalytics is a Python library for analyzing photovoltaic system-level data. It organizes analytics functions into modules for quality control (data shifts, irradiance, weather, outliers, gaps, time checks), feature identification (inverter clipping, clear sky periods, day/night, tracker orientation, shading), system characterization, and metrics computation. The library returns boolean series for quality and feature functions, making it easy to filter or label PV time series data.

The package targets researchers and engineers working with solar data, building on established dependencies like numpy, pandas, scipy, and pvlib. It's designed to handle the specific data quality and feature extraction challenges common in PV system analysis, from detecting measurement anomalies to identifying operational modes like inverter clipping or clear sky conditions.

Use it for:

• Detect and isolate data shifts or anomalies in PV time series before feeding data into analysis pipelines.
• Identify periods of inverter clipping to assess system performance limitations and capacity factors.
• Label clear sky conditions and day/night periods for benchmarking PV system performance against models.
• Validate irradiance and weather measurements for physical plausibility before using in system analysis.
• Extract system characteristics like nameplate power and orientation from operational data.
• Compute system-level metrics and KPIs for performance monitoring and reporting.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

PVAnalytics provides quality control, filtering, feature labeling, and analysis functions for photovoltaic system-level data, organized into modules for data quality checks, feature identification, system characterization, and metrics computation.

Yes. PVAnalytics is actively maintained, has low install friction, carries no known vulnerabilities, and offers a focused toolkit for a specific domain (PV analytics). The MIT license is permissive. Install it if you work with photovoltaic system data and need quality control, feature labeling, or system characterization functions; the modular design lets you use only what you need.

Install

pvanalytics on PyPI

pip install pvanalytics

uv add pvanalytics

poetry add pvanalytics

Installing pvanalytics

Before you install

Low install friction with a pure Python wheel distribution. Actively maintained as of 2026-07-08 with 140 repository stars. Depends on established scientific libraries (numpy, pandas, scipy, scikit-image, statsmodels) and pvlib, all widely used in the solar analytics domain.

License in practice

MIT license is permissive, allowing use in commercial and proprietary projects with minimal restrictions beyond attribution.

Quickstart

pip install pvanalytics

import pvanalytics
from pvanalytics.quality import irradiance

# Example: check irradiance data quality
valid_data = irradiance.check_irradiance_quality(irradiance_series)

Verify before relying

• Specific Python version requirements (requires_python field is unspecified in metadata)
• Whether all quality and feature modules are production-ready or still experimental given Beta status
• Performance characteristics with large time series datasets

Package facts

Evidence: pvanalytics-0.2.2-py3-none-any.whl

Tags

More Scientific/Engineering packages