wip

pipeline/generators/estimate_histplot.py

@@ -1,6 +1,32 @@
-from ..run import Run
 from pathlib import Path
 from typing import Generator
+import matplotlib.pyplot as plt
+import seaborn as sns
+import pandas as pd
+from ..utils import style_plot
 
-def generate_estimate_histplot(run: Run) -> Generator[Path]:
-    raise NotImplementedError
+def generate_estimate_histplot(output_dir: Path, df: pd.DataFrame, **kwargs) -> Generator[Path]:
+    """
+    Generates a styled histogram of the distribution of midpoint time estimates.
+    """
+    style_plot()
+    OUTPUT_PATH = output_dir / "estimate_distribution_histplot.png"
+
+    fig, ax = plt.subplots()
+
+    sns.histplot(
+        data=df,
+        x='estimate_midpoint',
+        log_scale=True,
+        ax=ax
+    )
+
+    ax.set_xlabel("Task Time (minutes, log scale)")
+    ax.set_ylabel("Number of Tasks")
+    ax.set_title("Distribution of Time Estimates for Atomic Tasks")
+
+    plt.tight_layout()
+    plt.savefig(OUTPUT_PATH)
+    plt.close(fig)
+
+    yield OUTPUT_PATH