datapilot-kit 0.3.0rc1__tar.gz

datapilot_kit-0.3.0rc1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Avishkar Gopale
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

datapilot_kit-0.3.0rc1/MANIFEST.in

@@ -0,0 +1,17 @@
+include LICENSE
+include README.md
+
+graft datapilot
+
+prune .venv
+prune datapilot-test
+prune build
+prune dist
+prune reports
+prune datasets
+prune docs
+prune scripts
+prune tests
+
+global-exclude *.py[cod]
+global-exclude __pycache__

datapilot_kit-0.3.0rc1/PKG-INFO

@@ -0,0 +1,103 @@
+Metadata-Version: 2.4
+Name: datapilot-kit
+Version: 0.3.0rc1
+Summary: An open-source Python library for deterministic exploratory data analysis and dataset understanding.
+Author: Avishkar D. Gopale
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/Aviii-3085/datapilot
+Project-URL: Repository, https://github.com/Aviii-3085/datapilot
+Project-URL: Issues, https://github.com/Aviii-3085/datapilot/issues
+Project-URL: Documentation, https://github.com/Aviii-3085/datapilot/tree/main/docs
+Keywords: eda,exploratory-data-analysis,data-analysis,data-science,dataset-profiling,machine-learning,analytics,python
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Intended Audience :: Education
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas>=2.2
+Requires-Dist: numpy>=2.0
+Requires-Dist: scipy>=1.14
+Requires-Dist: matplotlib>=3.9
+Requires-Dist: plotly>=6.0
+Requires-Dist: jinja2>=3.1
+Requires-Dist: rich>=14.0
+Requires-Dist: typer>=0.16
+Provides-Extra: dev
+Requires-Dist: black; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+Requires-Dist: mypy; extra == "dev"
+Requires-Dist: pytest; extra == "dev"
+Dynamic: license-file
+
+# Datapilot
+
+> **The first step after loading your dataset.**
+
+Datapilot is an open-source Python library that automates exploratory data analysis by generating deterministic dataset insights, health assessments, statistical summaries, and professional HTML reports.
+
+Every data project begins with understanding the data. Datapilot helps you understand your dataset before building machine learning models, dashboards, or AI-powered applications.
+
+---
+
+## Installation
+
+```bash
+pip install datapilot-kit
+```
+
+---
+
+## Quick Start
+
+```python
+import pandas as pd
+
+from datapilot import analyze
+
+df = pd.read_csv("dataset.csv")
+
+report = analyze(df)
+```
+
+---
+
+## Features
+
+- Dataset Summary
+- Dataset Health Score
+- Missing Value Analysis
+- Duplicate Detection
+- Data Type Analysis
+- Statistical Summaries
+- Outlier Detection
+- Correlation Analysis
+- Actionable Insights
+- Professional HTML Reports
+
+---
+
+## Documentation
+
+Project documentation is available in the `docs/` directory.
+
+- Vision
+- User Journey
+- API Philosophy
+- API Review
+- Roadmap
+
+---
+
+## Status
+
+🚧 Datapilot v0.3 — Public Preview (In Development)
+
+The project is currently being prepared for its first public release.

datapilot_kit-0.3.0rc1/README.md

@@ -0,0 +1,64 @@
+# Datapilot
+
+> **The first step after loading your dataset.**
+
+Datapilot is an open-source Python library that automates exploratory data analysis by generating deterministic dataset insights, health assessments, statistical summaries, and professional HTML reports.
+
+Every data project begins with understanding the data. Datapilot helps you understand your dataset before building machine learning models, dashboards, or AI-powered applications.
+
+---
+
+## Installation
+
+```bash
+pip install datapilot-kit
+```
+
+---
+
+## Quick Start
+
+```python
+import pandas as pd
+
+from datapilot import analyze
+
+df = pd.read_csv("dataset.csv")
+
+report = analyze(df)
+```
+
+---
+
+## Features
+
+- Dataset Summary
+- Dataset Health Score
+- Missing Value Analysis
+- Duplicate Detection
+- Data Type Analysis
+- Statistical Summaries
+- Outlier Detection
+- Correlation Analysis
+- Actionable Insights
+- Professional HTML Reports
+
+---
+
+## Documentation
+
+Project documentation is available in the `docs/` directory.
+
+- Vision
+- User Journey
+- API Philosophy
+- API Review
+- Roadmap
+
+---
+
+## Status
+
+🚧 Datapilot v0.3 — Public Preview (In Development)
+
+The project is currently being prepared for its first public release.

datapilot_kit-0.3.0rc1/datapilot/__init__.py

@@ -0,0 +1,11 @@
+"""
+Datapilot
+
+An intelligent Python library for exploratory data analysis.
+"""
+
+__version__ = "0.3.0rc1"
+
+from .api import analyze
+
+__all__ = ["analyze"]

datapilot_kit-0.3.0rc1/datapilot/analysis/__init__.py

@@ -0,0 +1,3 @@
+"""
+Analysis modules for Datapilot.
+"""

datapilot_kit-0.3.0rc1/datapilot/analysis/correlation.py

@@ -0,0 +1,58 @@
+"""
+Correlation analysis for Datapilot.
+"""
+
+from typing import SupportsFloat, cast
+
+import pandas as pd
+
+from .models import CorrelationSummary
+
+
+def generate_correlation_summary(
+    dataframe: pd.DataFrame,
+) -> CorrelationSummary:
+    """
+    Generate Pearson correlation analysis for numeric columns.
+    """
+
+    numeric_dataframe = dataframe.select_dtypes(
+        include="number",
+    )
+
+    correlation_matrix = numeric_dataframe.corr()
+
+    strong_positive_pairs: dict[str, float] = {}
+    strong_negative_pairs: dict[str, float] = {}
+
+    columns = list(correlation_matrix.columns)
+
+    for i, left in enumerate(columns):
+        for right in columns[i + 1:]:
+
+            correlation = cast(
+                SupportsFloat,
+                correlation_matrix.loc[left, right],
+            )
+
+            value = float(correlation)
+
+            pair = f"{left} ↔ {right}"
+
+            if value >= 0.70:
+                strong_positive_pairs[pair] = round(
+                    value,
+                    3,
+                )
+
+            elif value <= -0.70:
+                strong_negative_pairs[pair] = round(
+                    value,
+                    3,
+                )
+
+    return CorrelationSummary(
+        correlation_matrix=correlation_matrix,
+        strong_positive_pairs=strong_positive_pairs,
+        strong_negative_pairs=strong_negative_pairs,
+    )

datapilot_kit-0.3.0rc1/datapilot/analysis/datatype.py

@@ -0,0 +1,48 @@
+"""
+Data type analysis for Datapilot.
+"""
+
+import pandas as pd
+
+from .models import DataTypeSummary
+
+
+def generate_data_type_summary(
+    dataframe: pd.DataFrame,
+) -> DataTypeSummary:
+    """
+    Generate data type statistics for a dataset.
+
+    Parameters
+    ----------
+    dataframe : pandas.DataFrame
+        Dataset to analyze.
+
+    Returns
+    -------
+    DataTypeSummary
+        Summary of dataset column types.
+    """
+
+    numeric_columns = dataframe.select_dtypes(
+        include=["number"]
+    ).columns.tolist()
+
+    categorical_columns = dataframe.select_dtypes(
+    include=["object", "string", "category"]
+    ).columns.tolist()
+
+    boolean_columns = dataframe.select_dtypes(
+        include=["bool"]
+    ).columns.tolist()
+
+    datetime_columns = dataframe.select_dtypes(
+        include=["datetime", "datetimetz"]
+    ).columns.tolist()
+
+    return DataTypeSummary(
+        numeric_columns=numeric_columns,
+        categorical_columns=categorical_columns,
+        boolean_columns=boolean_columns,
+        datetime_columns=datetime_columns,
+    )

datapilot_kit-0.3.0rc1/datapilot/analysis/duplicate.py

@@ -0,0 +1,40 @@
+"""
+Duplicate row analysis for Datapilot.
+"""
+
+import pandas as pd
+
+from .models import DuplicateSummary
+
+
+def generate_duplicate_summary(
+    dataframe: pd.DataFrame,
+) -> DuplicateSummary:
+    """
+    Generate duplicate row statistics for a dataset.
+
+    Parameters
+    ----------
+    dataframe : pandas.DataFrame
+        Dataset to analyze.
+
+    Returns
+    -------
+    DuplicateSummary
+        Summary of duplicate rows in the dataset.
+    """
+
+    total_duplicates = int(dataframe.duplicated().sum())
+
+    total_rows = len(dataframe)
+
+    duplicate_percentage = (
+        round((total_duplicates / total_rows) * 100, 2)
+        if total_rows > 0
+        else 0.0
+    )
+
+    return DuplicateSummary(
+        total_duplicates=total_duplicates,
+        duplicate_percentage=duplicate_percentage,
+    )

datapilot_kit-0.3.0rc1/datapilot/analysis/health.py

@@ -0,0 +1,163 @@
+"""
+Dataset health assessment for Datapilot.
+"""
+
+import pandas as pd
+
+from .datatype import generate_data_type_summary
+from .duplicate import generate_duplicate_summary
+from .missing import generate_missing_value_summary
+from .models import DatasetHealth
+
+
+def generate_dataset_health(
+    dataframe: pd.DataFrame,
+) -> DatasetHealth:
+    """
+    Generate an overall health assessment for a dataset.
+    """
+
+    missing = generate_missing_value_summary(dataframe)
+    duplicates = generate_duplicate_summary(dataframe)
+    data_types = generate_data_type_summary(dataframe)
+
+    score = 100.0
+
+    # -----------------------------
+    # Missing Value Penalty (40 pts)
+    # -----------------------------
+    score -= (missing.missing_percentage / 100) * 40
+
+    # -----------------------------
+    # Duplicate Penalty (35 pts)
+    # -----------------------------
+    score -= (duplicates.duplicate_percentage / 100) * 35
+
+    # -----------------------------
+    # Structure Penalty (25 pts)
+    # -----------------------------
+    total_columns = len(dataframe.columns)
+
+    recognized_columns = (
+        len(data_types.numeric_columns)
+        + len(data_types.categorical_columns)
+        + len(data_types.boolean_columns)
+        + len(data_types.datetime_columns)
+    )
+
+    unrecognized_columns = max(
+        total_columns - recognized_columns,
+        0,
+    )
+
+    if total_columns > 0:
+        score -= (
+            unrecognized_columns / total_columns
+        ) * 25
+
+    score = max(0, min(100, round(score)))
+
+    # -----------------------------
+    # Grade
+    # -----------------------------
+    if score >= 95:
+        grade = "A+"
+        status = "Excellent"
+
+    elif score >= 90:
+        grade = "A"
+        status = "Healthy"
+
+    elif score >= 80:
+        grade = "B"
+        status = "Good"
+
+    elif score >= 70:
+        grade = "C"
+        status = "Fair"
+
+    elif score >= 60:
+        grade = "D"
+        status = "Poor"
+
+    else:
+        grade = "F"
+        status = "Critical"
+
+    # -----------------------------
+    # ML Readiness
+    # -----------------------------
+    ml_ready = (
+        score >= 85
+        and missing.missing_percentage <= 20
+        and duplicates.duplicate_percentage <= 5
+    )
+
+    # -----------------------------
+    # Strengths
+    # -----------------------------
+    strengths = []
+
+    if missing.total_missing == 0:
+        strengths.append("No missing values detected.")
+
+    if duplicates.total_duplicates == 0:
+        strengths.append("No duplicate rows detected.")
+
+    if unrecognized_columns == 0:
+        strengths.append("All columns have recognized data types.")
+
+    # -----------------------------
+    # Weaknesses
+    # -----------------------------
+    weaknesses = []
+
+    if missing.total_missing > 0:
+        weaknesses.append(
+            f"{missing.total_missing} missing values detected."
+        )
+
+    if duplicates.total_duplicates > 0:
+        weaknesses.append(
+            f"{duplicates.total_duplicates} duplicate rows detected."
+        )
+
+    if unrecognized_columns > 0:
+        weaknesses.append(
+            f"{unrecognized_columns} columns have unsupported data types."
+        )
+
+    # -----------------------------
+    # Recommendations
+    # -----------------------------
+    recommendations = []
+
+    if missing.missing_percentage > 0:
+        recommendations.append(
+            "Handle missing values before further analysis."
+        )
+
+    if duplicates.total_duplicates > 0:
+        recommendations.append(
+            "Remove duplicate rows."
+        )
+
+    if unrecognized_columns > 0:
+        recommendations.append(
+            "Review unsupported column data types."
+        )
+
+    if not recommendations:
+        recommendations.append(
+            "Dataset is ready for analysis."
+        )
+
+    return DatasetHealth(
+        score=score,
+        grade=grade,
+        status=status,
+        ml_ready=ml_ready,
+        strengths=strengths,
+        weaknesses=weaknesses,
+        recommendations=recommendations,
+    )

datapilot_kit-0.3.0rc1/datapilot/analysis/insights.py

@@ -0,0 +1,101 @@
+"""
+Insight generation for Datapilot.
+"""
+
+import pandas as pd
+
+from .correlation import generate_correlation_summary
+from .duplicate import generate_duplicate_summary
+from .missing import generate_missing_value_summary
+from .models import InsightSummary
+from .outliers import generate_outlier_summary
+
+
+def generate_insight_summary(
+    dataframe: pd.DataFrame,
+) -> InsightSummary:
+    """
+    Generate actionable dataset insights.
+    """
+
+    insights: list[str] = []
+
+    recommendations: list[str] = []
+
+    missing = generate_missing_value_summary(
+        dataframe
+    )
+
+    duplicates = generate_duplicate_summary(
+        dataframe
+    )
+
+    outliers = generate_outlier_summary(
+        dataframe
+    )
+
+    correlation = generate_correlation_summary(
+        dataframe
+    )
+
+    if missing.total_missing > 0:
+
+        insights.append(
+            f"Dataset contains "
+            f"{missing.total_missing} missing values."
+        )
+
+        recommendations.append(
+            "Handle missing values before "
+            "training machine learning models."
+        )
+
+    if duplicates.total_duplicates > 0:
+
+        insights.append(
+            f"Dataset contains "
+            f"{duplicates.total_duplicates} duplicate rows."
+        )
+
+        recommendations.append(
+            "Remove duplicate rows."
+        )
+
+    if outliers.total_outliers > 0:
+
+        insights.append(
+            f"Detected "
+            f"{outliers.total_outliers} statistical outliers."
+        )
+
+        recommendations.append(
+            "Review outliers before modelling."
+        )
+
+    if correlation.strong_positive_pairs:
+
+        insights.append(
+            "Highly correlated numeric features detected."
+        )
+
+        recommendations.append(
+            "Review correlated features to "
+            "reduce multicollinearity."
+        )
+
+    if correlation.strong_negative_pairs:
+
+        insights.append(
+            "Strong negative correlations detected."
+        )
+
+    if not insights:
+
+        insights.append(
+            "No significant data quality issues detected."
+        )
+
+    return InsightSummary(
+        insights=insights,
+        recommendations=recommendations,
+    )

datapilot_kit-0.3.0rc1/datapilot/analysis/missing.py

@@ -0,0 +1,56 @@
+"""
+Missing value analysis for Datapilot.
+"""
+
+import pandas as pd
+
+from .models import MissingValueSummary
+
+
+def generate_missing_value_summary(
+    dataframe: pd.DataFrame,
+) -> MissingValueSummary:
+    """
+    Generate missing value statistics for a dataset.
+
+    Parameters
+    ----------
+    dataframe : pandas.DataFrame
+        Dataset to analyze.
+
+    Returns
+    -------
+    MissingValueSummary
+        Summary of missing values in the dataset.
+    """
+
+    total_missing = int(dataframe.isna().sum().sum())
+
+    total_cells = dataframe.shape[0] * dataframe.shape[1]
+
+    missing_percentage = (
+        round((total_missing / total_cells) * 100, 2)
+        if total_cells > 0
+        else 0.0
+    )
+
+    missing_per_column = dataframe.isna().sum()
+
+    columns_with_missing = {
+        str(column): int(count)
+        for column, count in missing_per_column.items()
+        if count > 0
+    }
+
+    columns_without_missing = [
+        str(column)
+        for column, count in missing_per_column.items()
+        if count == 0
+    ]
+
+    return MissingValueSummary(
+        total_missing=total_missing,
+        missing_percentage=missing_percentage,
+        columns_with_missing=columns_with_missing,
+        columns_without_missing=columns_without_missing,
+    )