From 7daa19b987228ae878227a136c869e35c19b85b8 Mon Sep 17 00:00:00 2001
From: Alexandra Udaltsova <43303448+AUdaltsova@users.noreply.github.com>
Date: Mon, 5 Aug 2024 16:05:42 +0100
Subject: [PATCH 1/3] Fix history bug and add bells in analysis.py

---
 experiments/analysis.py | 29 ++++++++++++++++-------------
 1 file changed, 16 insertions(+), 13 deletions(-)

diff --git a/experiments/analysis.py b/experiments/analysis.py
index 75b00cd9..9d7d35f9 100644
--- a/experiments/analysis.py
+++ b/experiments/analysis.py
@@ -16,10 +16,11 @@ def main(runs: list[str], run_names: list[str]) -> None:
     """
     api = wandb.Api()
     dfs = []
+    epoch_num = []
     for run in runs:
-        run = api.run(f"openclimatefix/india/{run}")
+        run = api.run(f"openclimatefix/PROJECT/{run}")
 
-        df = run.history()
+        df = run.history(samples=run.lastHistoryStep+1)
         # Get the columns that are in the format 'MAE_horizon/step_<number>/val`
         mae_cols = [col for col in df.columns if "MAE_horizon/step_" in col and "val" in col]
         # Sort them
@@ -40,6 +41,7 @@ def main(runs: list[str], run_names: list[str]) -> None:
         # Get the step from the column name
         column_timesteps = [int(col.split("_")[-1].split("/")[0]) * 15 for col in mae_cols]
         dfs.append(df)
+        epoch_num.append(min_row_idx)
     # Get the timedelta for each group
     groupings = [
         [0, 0],
@@ -89,22 +91,22 @@ def main(runs: list[str], run_names: list[str]) -> None:
     # Plot the error on per timestep, and all timesteps
     plt.figure()
     for idx, df in enumerate(dfs):
-        plt.plot(column_timesteps, df, label=run_names[idx])
-    plt.legend()
-    plt.xlabel("Timestep (minutes)")
-    plt.ylabel("MAE %")
-    plt.title("MAE % for each timestep")
+        plt.plot(column_timesteps, df, label=f"{run_names[idx]}, epoch: {epoch_num[idx]}")
+    plt.legend(fontsize=18)
+    plt.xlabel("Timestep (minutes)", fontsize=18)
+    plt.ylabel("MAE %", fontsize=18)
+    plt.title("MAE % for each timestep", fontsize=24)
     plt.savefig("mae_per_timestep.png")
     plt.show()
 
     # Plot the error on per timestep, and grouped timesteps
     plt.figure()
-    for run_name in run_names:
-        plt.plot(groups_df[run_name], label=run_name)
-    plt.legend()
-    plt.xlabel("Timestep (minutes)")
-    plt.ylabel("MAE %")
-    plt.title("MAE % for each timestep")
+    for idx, run_name in enumerate(run_names):
+        plt.plot(groups_df[run_name], label=f"{run_name}, epoch: {epoch_num[idx]}")
+    plt.legend(fontsize=18)
+    plt.xlabel("Timestep (minutes)", fontsize=18)
+    plt.ylabel("MAE %", fontsize=18)
+    plt.title("MAE % for each timestep", fontsize=24)
     plt.savefig("mae_per_timestep.png")
     plt.show()
 
@@ -119,3 +121,4 @@ def main(runs: list[str], run_names: list[str]) -> None:
     parser.add_argument("--run_names", nargs="+")
     args = parser.parse_args()
     main(args.list_of_runs, args.run_names)
+    

From e268a61fdc9c3d487038a96be7cbdeab90c0e1df Mon Sep 17 00:00:00 2001
From: Alexandra Udaltsova <43303448+AUdaltsova@users.noreply.github.com>
Date: Mon, 5 Aug 2024 16:14:37 +0100
Subject: [PATCH 2/3] Update analysis.py

---
 experiments/analysis.py | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/experiments/analysis.py b/experiments/analysis.py
index 9d7d35f9..33fc718d 100644
--- a/experiments/analysis.py
+++ b/experiments/analysis.py
@@ -92,10 +92,10 @@ def main(runs: list[str], run_names: list[str]) -> None:
     plt.figure()
     for idx, df in enumerate(dfs):
         plt.plot(column_timesteps, df, label=f"{run_names[idx]}, epoch: {epoch_num[idx]}")
-    plt.legend(fontsize=18)
-    plt.xlabel("Timestep (minutes)", fontsize=18)
-    plt.ylabel("MAE %", fontsize=18)
-    plt.title("MAE % for each timestep", fontsize=24)
+    plt.legend()
+    plt.xlabel("Timestep (minutes)")
+    plt.ylabel("MAE %")
+    plt.title("MAE % for each timestep")
     plt.savefig("mae_per_timestep.png")
     plt.show()
 
@@ -103,10 +103,10 @@ def main(runs: list[str], run_names: list[str]) -> None:
     plt.figure()
     for idx, run_name in enumerate(run_names):
         plt.plot(groups_df[run_name], label=f"{run_name}, epoch: {epoch_num[idx]}")
-    plt.legend(fontsize=18)
-    plt.xlabel("Timestep (minutes)", fontsize=18)
-    plt.ylabel("MAE %", fontsize=18)
-    plt.title("MAE % for each timestep", fontsize=24)
+    plt.legend()
+    plt.xlabel("Timestep (minutes)")
+    plt.ylabel("MAE %")
+    plt.title("MAE % for each timestep")
     plt.savefig("mae_per_timestep.png")
     plt.show()
 

From f928e801200329188d9567de23efd9b30ba0fd7f Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Mon, 5 Aug 2024 15:16:57 +0000
Subject: [PATCH 3/3] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 experiments/analysis.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/experiments/analysis.py b/experiments/analysis.py
index 33fc718d..bb119664 100644
--- a/experiments/analysis.py
+++ b/experiments/analysis.py
@@ -20,7 +20,7 @@ def main(runs: list[str], run_names: list[str]) -> None:
     for run in runs:
         run = api.run(f"openclimatefix/PROJECT/{run}")
 
-        df = run.history(samples=run.lastHistoryStep+1)
+        df = run.history(samples=run.lastHistoryStep + 1)
         # Get the columns that are in the format 'MAE_horizon/step_<number>/val`
         mae_cols = [col for col in df.columns if "MAE_horizon/step_" in col and "val" in col]
         # Sort them
@@ -121,4 +121,3 @@ def main(runs: list[str], run_names: list[str]) -> None:
     parser.add_argument("--run_names", nargs="+")
     args = parser.parse_args()
     main(args.list_of_runs, args.run_names)
-