From a545c8b1c61e1a4d402baf120de248a9d432a190 Mon Sep 17 00:00:00 2001 From: Simeon Wong Date: Sun, 4 Feb 2024 22:30:34 -0500 Subject: [PATCH 1/4] bugfix: only compute mean of Min Delay, cannot mean non numeric values --- Analyze.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Analyze.py b/Analyze.py index 3f07dbf..a4ce6d2 100644 --- a/Analyze.py +++ b/Analyze.py @@ -14,7 +14,7 @@ def compute_avg_delay(data): """ Compute the average delay for each route """ - return data.groupby('Route').mean().reset_index() + return data.groupby('Route')['Min Delay'].mean().reset_index() def main(): From bc0e903fbf6c31faa0ee677246fe38879768a0c3 Mon Sep 17 00:00:00 2001 From: Simeon Wong Date: Sun, 4 Feb 2024 22:54:46 -0500 Subject: [PATCH 2/4] feature: group by arbitrary columns --- Analyze.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/Analyze.py b/Analyze.py index 3f07dbf..048bcae 100644 --- a/Analyze.py +++ b/Analyze.py @@ -10,11 +10,11 @@ def import_data(): return pd.read_csv('ttc-bus-delay-data-2023.csv') -def compute_avg_delay(data): +def compute_avg_delay(data, group_by: str = 'Route'): """ - Compute the average delay for each route + Compute the average delay aggregated by specified column """ - return data.groupby('Route').mean().reset_index() + return data.groupby(group_by).mean().reset_index() def main(): From b079b371df0e610015b25b17d821715511ccb1ae Mon Sep 17 00:00:00 2001 From: Simeon Wong Date: Mon, 5 Feb 2024 10:51:33 -0500 Subject: [PATCH 3/4] specify grouping directly in compute_avg_delay function call --- Analyze.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Analyze.py b/Analyze.py index 048bcae..1512d02 100644 --- a/Analyze.py +++ b/Analyze.py @@ -22,7 +22,7 @@ def main(): Main function """ data = import_data() - avg_delay = compute_avg_delay(data) + avg_delay = compute_avg_delay(data, group_by='Route') plt.hist(avg_delay['Min Delay'], bins=30) plt.title('Average Delay Distribution') From 831df25811c76eb91a43e4975a5ed42e0dcd40b7 Mon Sep 17 00:00:00 2001 From: niyazmnazari Date: Mon, 12 Feb 2024 12:16:55 -0500 Subject: [PATCH 4/4] Add Year to Title --- Analyze.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Analyze.py b/Analyze.py index 3f07dbf..f07026b 100644 --- a/Analyze.py +++ b/Analyze.py @@ -25,7 +25,7 @@ def main(): avg_delay = compute_avg_delay(data) plt.hist(avg_delay['Min Delay'], bins=30) - plt.title('Average Delay Distribution') + plt.title('Average Delay Distribution 2023') plt.xlabel('Average Delay (minutes)')