From 03be0758bad63d21ddfa82a2c565d7617f2135f4 Mon Sep 17 00:00:00 2001
From: Claude <noreply@anthropic.com>
Date: Thu, 26 Mar 2026 16:46:31 +0000
Subject: [PATCH] Add Orioles pitcher Predict+ output to daily pipeline

For MLB games, identifies Baltimore Orioles pitchers from yesterday's
Statcast data (via home_team/away_team + inning_topbot) and outputs
their Predict+ scores for anyone who threw >= 10 pitches. Results are
printed to console, saved as orioles_{day}.csv alongside the main CSV,
and rendered as a markdown table in the GitHub Actions step summary.

https://claude.ai/code/session_01XnaxiNLWNzGJXwyftRiGxr
---
 .github/workflows/daily-analysis.yml | 29 ++++++++++++++
 run_daily.R                          | 60 ++++++++++++++++++++++++++++
 2 files changed, 89 insertions(+)

diff --git a/.github/workflows/daily-analysis.yml b/.github/workflows/daily-analysis.yml
index 1fe526e..6afa717 100644
--- a/.github/workflows/daily-analysis.yml
+++ b/.github/workflows/daily-analysis.yml
@@ -249,6 +249,35 @@ jobs:
             echo "### Output Files" >> $GITHUB_STEP_SUMMARY
             echo "- CSV: \`${CSV}\`" >> $GITHUB_STEP_SUMMARY
             echo "- Visualizations: \`output/${{ steps.check_outputs.outputs.year }}/${{ steps.check_outputs.outputs.month }}/visualizations/\`" >> $GITHUB_STEP_SUMMARY
+
+            # Orioles pitcher summary (MLB only)
+            if [ "${LEVEL}" == "MLB" ]; then
+              YEAR=${{ steps.check_outputs.outputs.year }}
+              MONTH=${{ steps.check_outputs.outputs.month }}
+              DAY=$(date -d "$DATE" '+%d')
+              ORIOLES_CSV="output/${YEAR}/${MONTH}/orioles_${DAY}.csv"
+
+              echo "" >> $GITHUB_STEP_SUMMARY
+              echo "### Baltimore Orioles Pitcher Predict+ Scores (≥ 10 pitches)" >> $GITHUB_STEP_SUMMARY
+              echo "" >> $GITHUB_STEP_SUMMARY
+
+              if [ -f "$ORIOLES_CSV" ]; then
+                python3 - "$ORIOLES_CSV" >> $GITHUB_STEP_SUMMARY << 'PYEOF'
+import csv, sys
+rows = list(csv.DictReader(open(sys.argv[1])))
+if rows:
+    print("| Pitcher | Role | Pitches | Predict+ | Status |")
+    print("|---------|------|---------|----------|--------|")
+    for r in rows:
+        pplus = f"{float(r['predict_plus']):.1f}" if r.get('predict_plus') else "N/A"
+        print(f"| {r['pitcher_name']} | {r['role']} | {r['n_pitches_test']} | {pplus} | {r['status']} |")
+else:
+    print("No Orioles pitchers threw ≥ 10 pitches.")
+PYEOF
+              else
+                echo "No Orioles pitchers appeared (or no team data available)." >> $GITHUB_STEP_SUMMARY
+              fi
+            fi
           else
             echo "**Status:** No output generated" >> $GITHUB_STEP_SUMMARY
           fi
diff --git a/run_daily.R b/run_daily.R
index 6001350..4dd84d9 100644
--- a/run_daily.R
+++ b/run_daily.R
@@ -530,3 +530,63 @@ cat("  CSV:     ", OUT_CSV, "\n")
 cat("  Model:   ", OUT_MODEL, "\n")
 cat("  Visuals: ", viz_output, "/\n", sep = "")
 cat("============================================================\n\n")
+
+# ============================================================================
+# BALTIMORE ORIOLES PITCHER SUMMARY
+# ============================================================================
+
+if (LEVEL == "MLB") {
+  orioles_ppi <- NULL
+
+  if (all(c("home_team", "away_team", "inning_topbot") %in% names(df_test))) {
+    # Determine each pitcher's team from test data:
+    # TOP of inning → home team is pitching; BOT of inning → away team is pitching
+    pitcher_team_map <- df_test %>%
+      dplyr::mutate(
+        pitcher_team = dplyr::if_else(
+          stringr::str_to_upper(.data$inning_topbot) == "TOP",
+          as.character(.data$home_team),
+          as.character(.data$away_team)
+        )
+      ) %>%
+      dplyr::filter(!is.na(.data$pitcher_id), !is.na(.data$pitcher_team)) %>%
+      dplyr::distinct(.data$pitcher_id, .data$pitcher_team) %>%
+      dplyr::group_by(.data$pitcher_id) %>%
+      dplyr::slice(1) %>%
+      dplyr::ungroup()
+
+    orioles_pitcher_ids <- pitcher_team_map %>%
+      dplyr::filter(.data$pitcher_team == "BAL") %>%
+      dplyr::pull(.data$pitcher_id)
+
+    if (length(orioles_pitcher_ids) > 0) {
+      orioles_ppi <- pitcher_ppi %>%
+        dplyr::filter(.data$pitcher_id %in% orioles_pitcher_ids,
+                      .data$n_pitches_test >= 10) %>%
+        dplyr::arrange(dplyr::desc(.data$predict_plus))
+    }
+  }
+
+  cat("============================================================\n")
+  cat("  Baltimore Orioles Pitchers (>= 10 pitches)\n")
+  cat("============================================================\n")
+
+  if (!is.null(orioles_ppi) && nrow(orioles_ppi) > 0) {
+    orioles_display <- orioles_ppi %>%
+      dplyr::select(
+        .data$pitcher_name, .data$role, .data$n_pitches_test,
+        .data$predict_plus, .data$status
+      )
+    print(as.data.frame(orioles_display), row.names = FALSE)
+
+    OUT_ORIOLES_CSV <- file.path(output_base, paste0("orioles_", target_day, ".csv"))
+    readr::write_csv(orioles_ppi, OUT_ORIOLES_CSV)
+    cat("\nOrioles CSV saved: ", OUT_ORIOLES_CSV, "\n")
+  } else if (!all(c("home_team", "away_team") %in% names(df_test))) {
+    cat("Team data not available in Statcast download.\n")
+  } else {
+    cat("No Orioles pitchers threw >= 10 pitches.\n")
+  }
+
+  cat("============================================================\n\n")
+}