dylan/crosspost
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity

refactor: update analysis classes to accept DataFrame as parameter instead of instance variable

Browse Source
This commit is contained in:
Dylan De Faoite
2026-03-01 16:25:39 +00:00
parent d20790ed4b
commit 07ab7529a9
7 changed files with 403 additions and 389 deletions
Download Patch File Download Diff File Expand all files Collapse all files

63
server/analysis/temporal.py
View File

@@ -1,16 +1,14 @@
import pandas as pd
class TemporalAnalysis:
def __init__(self, df: pd.DataFrame):
self.df = df
def avg_reply_time_per_emotion(self) -> dict:
df = self.df.copy()
def avg_reply_time_per_emotion(self, df: pd.DataFrame) -> list[dict]:
df = df.copy()
replies = df[
(df["type"] == "comment") &
(df["reply_to"].notna()) &
(df["reply_to"] != "")
(df["type"] == "comment")
& (df["reply_to"].notna())
& (df["reply_to"] != "")
]
id_to_time = df.set_index("id")["dt"].to_dict()
@@ -23,48 +21,51 @@ class TemporalAnalysis:
return None
return (row["dt"] - parent_time).total_seconds()
replies["reply_time"] = replies.apply(compute_reply_time, axis=1)
emotion_cols = [col for col in df.columns if col.startswith("emotion_") and col not in ("emotion_neutral", "emotion_surprise")]
emotion_cols = [
col
for col in df.columns
if col.startswith("emotion_")
and col not in ("emotion_neutral", "emotion_surprise")
]
replies["dominant_emotion"] = replies[emotion_cols].idxmax(axis=1)
grouped = (
replies
.groupby("dominant_emotion")["reply_time"]
replies.groupby("dominant_emotion")["reply_time"]
.agg(["mean", "count"])
.reset_index()
)
return grouped.to_dict(orient="records")
def posts_per_day(self) -> dict:
per_day = (
self.df.groupby("date")
.size()
.reset_index(name="count")
)
def posts_per_day(self, df: pd.DataFrame) -> list[dict]:
per_day = df.groupby("date").size().reset_index(name="count")
return per_day.to_dict(orient="records")
def heatmap(self) -> dict:
def heatmap(self, df: pd.DataFrame) -> list[dict]:
weekday_order = [
"Monday", "Tuesday", "Wednesday",
"Thursday", "Friday", "Saturday", "Sunday"
"Monday",
"Tuesday",
"Wednesday",
"Thursday",
"Friday",
"Saturday",
"Sunday",
]
self.df["weekday"] = pd.Categorical(
self.df["weekday"],
categories=weekday_order,
ordered=True
df = df.copy()
df["weekday"] = pd.Categorical(
df["weekday"], categories=weekday_order, ordered=True
)
heatmap = (
self.df
.groupby(["weekday", "hour"], observed=True)
df.groupby(["weekday", "hour"], observed=True)
.size()
.unstack(fill_value=0)
.reindex(columns=range(24), fill_value=0)
)
heatmap.columns = heatmap.columns.map(str)
return heatmap.to_dict(orient="records")
return heatmap.to_dict(orient="records")