Modfiy task for fit AR model so that relevant output is also saved as an .tex file.

Author: Lenr4

src/lennart_epp/analysis/task_fit_ar_model.py

@@ -7,30 +7,50 @@
 def task_evaluate_ar_models(
     script=SRC / "analysis" / "evaluate_ar_model.py",
     data=BLD / "data" / "cleaned_apple_data.pkl",
-    produces=BLD / "models" / "ar_model_evaluation.pkl",
+    produces=(
+        BLD / "models" / "ar_model_evaluation.pkl",
+        BLD / "models" / "top_models.tex",
+    ),
     max_p=15,
     criterion="aic",
 ):
-    """Evaluate AR(p) models and save top models and metrics."""
     df = pd.read_pickle(data)
-
     evaluation_results = evaluate_ar_models(df, max_p=max_p, criterion=criterion)
 
-    top_models_data = evaluation_results.get("top_models", [])
-    metrics_data = evaluation_results.get("model_metrics", [])
-    metadata_data = evaluation_results.get("metadata", {})
-
-    top_models_df = pd.DataFrame(top_models_data) if top_models_data else pd.DataFrame()
-    metrics_df = pd.DataFrame(metrics_data) if metrics_data else pd.DataFrame()
-    metadata_df = pd.DataFrame([metadata_data]) if metadata_data else pd.DataFrame()
-
-    results = {
-        "top_models": top_models_df,
-        "model_metrics": metrics_df,
-        "metadata": metadata_df,
-    }
-
-    produces.parent.mkdir(parents=True, exist_ok=True)
-    pd.to_pickle(results, produces)
-
-    assert produces.exists(), f"❌ Failed to produce {produces}"
+    produces[0].parent.mkdir(parents=True, exist_ok=True)
+    pd.to_pickle(evaluation_results, produces[0])
+    assert produces[0].exists(), f"❌ Failed to produce {produces[0]}"
+
+    top_models_df = pd.DataFrame(evaluation_results.get("top_models", []))
+
+    if not top_models_df.empty:
+        latex_table = top_models_df.drop(
+            columns=["coefficients", "integrated_coefficients"], errors="ignore"
+        )
+
+        expected_columns = ["p", "aic", "bic", "p_value", "differenced"]
+        latex_table = latex_table[
+            [col for col in expected_columns if col in latex_table.columns]
+        ]
+
+        with produces[1].open("w", encoding="utf-8") as f:
+            f.write("\\begin{table}[H]\n")
+            f.write("\\centering\n")
+            f.write("\\caption{Top AR Models}\n")
+            f.write("\\label{tab:top_models}\n")
+            f.write("\\begin{tabular}{|c|c|c|c|c|}\n")
+            f.write("\\hline\n")
+            f.write("p & AIC & BIC & p-value & Differenced \\\\\n")
+            f.write("\\hline\n")
+
+            for _, row in latex_table.iterrows():
+                f.write(
+                    f"{int(row['p'])} & {row['aic']:.3f} & {row['bic']:.3f} & "
+                    f"{row['p_value']:.5f} & {row['differenced']!s} \\\\\n"
+                )
+
+            f.write("\\hline\n")
+            f.write("\\end{tabular}\n")
+            f.write("\\end{table}\n")
+
+        assert produces[1].exists(), f"❌ Failed to produce {produces[1]}"