datapilot-kit 0.3.0rc1__py3-none-any.whl

datapilot/analysis/statistics.py

@@ -0,0 +1,46 @@
+"""
+Statistical analysis for Datapilot.
+"""
+
+from typing import SupportsFloat, cast
+
+import pandas as pd
+
+from .models import StatisticsSummary
+
+
+def generate_statistics_summary(
+    dataframe: pd.DataFrame,
+) -> StatisticsSummary:
+    """
+    Generate descriptive statistics for all numeric columns.
+    """
+
+    numeric_dataframe = dataframe.select_dtypes(
+        include="number",
+    )
+
+    statistics: dict[str, dict[str, float]] = {}
+
+    for column in numeric_dataframe.columns:
+        series = numeric_dataframe[column]
+
+        description = series.describe()
+
+        statistics[str(column)] = {
+            "count": float(cast(SupportsFloat, description["count"])),
+            "mean": float(cast(SupportsFloat, description["mean"])),
+            "median": float(cast(SupportsFloat, series.median())),
+            "std": float(cast(SupportsFloat, description["std"])),
+            "variance": float(cast(SupportsFloat, series.var())),
+            "min": float(cast(SupportsFloat, description["min"])),
+            "q1": float(cast(SupportsFloat, description["25%"])),
+            "q3": float(cast(SupportsFloat, description["75%"])),
+            "max": float(cast(SupportsFloat, description["max"])),
+            "skewness": float(cast(SupportsFloat, series.skew())),
+            "kurtosis": float(cast(SupportsFloat, series.kurt())),
+        }
+
+    return StatisticsSummary(
+        column_statistics=statistics,
+    )

datapilot/analysis/summary.py

@@ -0,0 +1,36 @@
+"""
+Dataset summary analysis for Datapilot.
+"""
+
+import pandas as pd
+
+from .models import DatasetSummary
+
+
+def generate_summary(dataframe: pd.DataFrame) -> DatasetSummary:
+    """
+    Generate a summary of the dataset.
+
+    Parameters
+    ----------
+    dataframe : pandas.DataFrame
+        Dataset to summarize.
+
+    Returns
+    -------
+    DatasetSummary
+        Summary information about the dataset.
+    """
+
+    memory_usage = float(
+        dataframe.memory_usage(deep=True).sum()
+        / 1024
+        / 1024
+    )
+
+    return DatasetSummary(
+        rows=dataframe.shape[0],
+        columns=dataframe.shape[1],
+        memory_usage_mb=round(memory_usage, 2),
+        column_names=list(dataframe.columns),
+    )

datapilot/api/__init__.py

@@ -0,0 +1,7 @@
+"""
+Public API for Datapilot.
+"""
+
+from .analyze import analyze
+
+__all__ = ["analyze"]

datapilot/api/analyze.py

@@ -0,0 +1,16 @@
+"""
+Public API for Datapilot.
+"""
+
+from typing import Any
+
+from ..core.loader import load_dataset
+from ..core.report import Report
+
+
+def analyze(data: Any) -> Report:
+    """
+    Analyze a dataset and return a Report object.
+    """
+    dataframe = load_dataset(data)
+    return Report(dataframe)