refactor for multiple series

foo.py

@@ -0,0 +1,103 @@
+import typing
+
+import pandas
+from dataclasses import dataclass
+from math import floor
+from datetime import datetime
+
+def load_score_log(path: str) -> pandas.DataFrame:
+    return 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')
+
+def generate_station_stats(score_log: pandas.DataFrame) -> pandas.DataFrame:
+    # 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)
+
+    # add total score
+    summary = pandas.merge(summary, score_log[['name', 'score']].groupby('name').sum(), on='name', validate='1:1')
+    summary.rename(columns={'score': 'total_score'}, inplace=True)
+
+    boosts = score_log[score_log['sourcename'] == 'Output Boost'][['name', 'score']].groupby('name')
+
+    # add total boosts
+    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')
+
+    # 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')
+
+    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.rename(columns={'score': 'totalvisits'}, inplace=True)
+
+    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.rename(columns={'score': 'captures'}, inplace=True)
+
+    # add max held duration (max capture score)
+    summary = pandas.merge(summary, captures.max(), on='name', validate='1:1')
+    summary.rename(columns={'score': 'maxheldduration'}, inplace=True)
+
+    # add total held duration (sum capture score)
+    summary = pandas.merge(summary, captures.sum(), on='name', validate='1:1')
+    summary.rename(columns={'score': 'totalheldduration'}, inplace=True)
+
+    return summary
+
+def generate_score_per_second(score_log: pandas.DataFrame) -> pandas.DataFrame:
+    @dataclass
+    class ScoreSecond:
+        name: str
+        sourcename: str
+        when: datetime
+        score: float
+        once: bool
+        mapx: int
+        mapy: int
+
+    def row_to_scoreseconds(row, score_per) -> typing.Iterator[ScoreSecond]:
+        seconds = int(floor(row.score / score_per))
+        assert row.score % score_per < 0.1
+        when = int(floor(row.when.timestamp()))
+        for elapsed in range(0, seconds):
+            timestamp = pandas.Timestamp(when - elapsed, unit='s')
+            yield ScoreSecond(name=row.name, sourcename=row.sourcename, mapx=row.mapx, mapy=row.mapy, when=timestamp,
+                              score=score_per, once=False)
+
+    def gen_scoreseconds() -> typing.Iterator[ScoreSecond]:
+        for row in score_log.itertuples():
+            if row.sourcename == "Capture":
+                yield from row_to_scoreseconds(row, 1.0)
+            elif row.sourcename == "Output Boost":
+                yield from row_to_scoreseconds(row, 0.1)
+            else:  # one-off
+                yield ScoreSecond(name=row.name, sourcename=row.sourcename, mapx=row.mapx, mapy=row.mapy, when=row.when,
+                                  score=row.score, once=True)
+
+    scoreseconds = pandas.DataFrame(gen_scoreseconds())
+    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)
+
+    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