add all series to graph

foo.py

@@ -5,19 +5,39 @@ from dataclasses import dataclass
 from math import floor
 from datetime import datetime
 
+def _add_accumulated_score(df: pandas.DataFrame):
+    acc_col = pandas.Series([0.0]).repeat(len(df)).reset_index(drop=True)
+
+    acc = 0.0
+    for i, row in enumerate(df.itertuples()):
+        acc += row.score
+        acc_col[i] = acc
+
+    df['accumulated_score'] = acc_col
+
 def load_score_log(path: str) -> pandas.DataFrame:
-    return pandas.read_csv(path, sep=',',
+    scores = pandas.read_csv(path, sep=',',
                            dtype={'score': int, 'sourcename': str, 'name': str, 'mapx': int, 'mapy': int},
                            parse_dates=['when'], date_format='%d/%m/%Y %H:%M')
+    scores.sort_values('when', inplace=True)
+    _add_accumulated_score(scores)
+    return scores
 
 def generate_station_stats(score_log: pandas.DataFrame) -> pandas.DataFrame:
+    station_count = len(score_log['name'].unique())
+
     # every station in the score log should have a first visit, so create summary based on that
     summary = score_log[score_log['sourcename'] == 'First Visit'][['name', 'mapx', 'mapy', 'when']]
     summary.rename(columns={'when': 'first_visit'}, inplace=True)
 
+    assert len(summary) == station_count
+
+    common_join_args = {'on':'name', 'how':'left', 'validate': '1:1'}
+
     # add total score
-    summary = pandas.merge(summary, score_log[['name', 'score']].groupby('name').sum(), on='name', validate='1:1')
+    summary = pandas.merge(summary, score_log[['name', 'score']].groupby('name').sum(), **common_join_args)
     summary.rename(columns={'score': 'total_score'}, inplace=True)
+    assert len(summary) == station_count
 
     boosts = score_log[score_log['sourcename'] == 'Output Boost'][['name', 'score']].groupby('name')
 
@@ -25,34 +45,40 @@ def generate_station_stats(score_log: pandas.DataFrame) -> pandas.DataFrame:
     total_boosts = boosts.sum()
     total_boosts['totalboostduration'] = total_boosts['score'].apply(lambda x: 10 * x)
     total_boosts.rename(columns={'score': 'totalboostscore'}, inplace=True)
-    summary = pandas.merge(summary, total_boosts, on='name')
+    summary = pandas.merge(summary, total_boosts, **common_join_args)
+    assert len(summary) == station_count
 
     # add max boosts
     max_boosts = boosts.max()
     max_boosts['maxboostduration'] = max_boosts['score'].apply(lambda x: 10 * x)
     max_boosts.rename(columns={'score': 'maxboostscore'}, inplace=True)
-    summary = pandas.merge(summary, max_boosts, on='name')
+    summary = pandas.merge(summary, max_boosts, **common_join_args)
+    assert len(summary) == station_count
 
     visits = score_log[(score_log['sourcename'] == 'Visit') | (score_log['sourcename'] == 'First Visit')][['name', 'score']].groupby('name')
 
     # add total visits (count)
-    summary = pandas.merge(summary, visits.count(), on='name', validate='1:1')
+    summary = pandas.merge(summary, visits.count(), **common_join_args)
     summary.rename(columns={'score': 'totalvisits'}, inplace=True)
+    assert len(summary) == station_count
 
     captures = score_log[score_log['sourcename'] == 'Capture'][['name', 'score']].groupby('name')
 
     # add captures (count)
-    summary = pandas.merge(summary, captures.count(), on='name', validate='1:1')
+    summary = pandas.merge(summary, captures.count(), **common_join_args)
     summary.rename(columns={'score': 'captures'}, inplace=True)
+    assert len(summary) == station_count
 
     # add max held duration (max capture score)
-    summary = pandas.merge(summary, captures.max(), on='name', validate='1:1')
+    summary = pandas.merge(summary, captures.max(), **common_join_args)
     summary.rename(columns={'score': 'maxheldduration'}, inplace=True)
+    assert len(summary) == station_count
 
     # add total held duration (sum capture score)
-    summary = pandas.merge(summary, captures.sum(), on='name', validate='1:1')
+    summary = pandas.merge(summary, captures.sum(), **common_join_args)
     summary.rename(columns={'score': 'totalheldduration'}, inplace=True)
 
+    assert len(summary) == station_count
     return summary
 
 def generate_score_per_second(score_log: pandas.DataFrame) -> pandas.DataFrame:
@@ -89,15 +115,5 @@ def generate_score_per_second(score_log: pandas.DataFrame) -> pandas.DataFrame:
     scoreseconds.sort_values(by=['when'], inplace=True)
     scoreseconds.reset_index(drop=True, inplace=True)
 
-    acc_col = pandas.Series([0.0]).repeat(len(scoreseconds)).reset_index(drop=True)
+    _add_accumulated_score(scoreseconds)
-
-    acc = 0.0
-    for i, row in enumerate(scoreseconds.itertuples()):
-        acc += row.score
-        acc_col[i] = acc
-
-    scoreseconds['accumulated_score'] = acc_col
-    del acc
-    del acc_col
-
     return scoreseconds