ben/vath
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

added argparse for job dir, added tone filter

Browse Source
This commit is contained in:
eulaly
2026-05-08 23:28:13 -04:00
parent afd5b8c60e
commit cc16acbb12
2 changed files with 14 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/tasks.org
View File

@@ -351,15 +351,13 @@ data pulls entirely from the job; goal is to point viz/streamlit.py at any job/
** evidence ** evidence
- commit: - commit:
- tests: from root dir, `streamlit run viz/streamlit.py` - tests: from root dir, `streamlit run viz/streamlit.py <job-dir>`
7. add forum_url, forum_collected_date to scraper
* [ ] t1.6 host streamlit * [ ] t1.6 host streamlit
figure out how to host this, locally or via streamlit servers figure out how to host this, locally or via streamlit servers
* === Backlog === * === Backlog ===
- add forum_url, forum_collected_date to scraper (to add to viz)
* [ ] X: complete proposal information * [ ] X: complete proposal information
Ensure we capture as much useful information as possible about the actual proposal - contact information, etc. what the state actually says about what was posted. Ensure we capture as much useful information as possible about the actual proposal - contact information, etc. what the state actually says about what was posted.
** acceptance criteria ** acceptance criteria

21
viz/streamlit.py
View File

@@ -1,14 +1,17 @@
# streamlit run analysis/viz/streamlit.py # streamlit run viz/streamlit.py -- --jobs-dir analysis/jobs/f452-1
import argparse import argparse
from pathlib import Path from pathlib import Path
from datetime import datetime as dt from datetime import datetime as dt
import pandas as pd import pandas as pd
import plotly.graph_objects as go import plotly.graph_objects as go
import plotly.express as px import plotly.express as px
import plotly.subplots as ps
import streamlit as st import streamlit as st
workdir = Path("analysis/jobs/f452-1") parser = argparse.ArgumentParser()
parser.add_argument("--jobs-dir", default="analysis/jobs/f452-1", type=Path,
help="Job directory containing review.csv, forum.jsonl, and prompt.txt")
args, _ = parser.parse_known_args() # parse_known_args: ignore Streamlit's own argv entries
workdir = args.jobs_dir
df = pd.read_csv(workdir/"review.csv") df = pd.read_csv(workdir/"review.csv")
df['date_dt'] = pd.to_datetime(df.date) df['date_dt'] = pd.to_datetime(df.date)
df["date_day"] = df["date_dt"].dt.date df["date_day"] = df["date_dt"].dt.date
@@ -128,14 +131,14 @@ st.subheader("Comment Explorer",anchor=False,divider="gray")
# comment explorer # comment explorer
cex_left, cex_right = st.columns([1,1]) cex_left, cex_right = st.columns([1,1])
with cex_left: with cex_left:
stance = st.multiselect("Filter stance", sorted(df["stance"].dropna().unique()), default=sorted(df["stance"].dropna().unique())) filter_stance = st.multiselect("Filter stance", sorted(df["stance"].dropna().unique()), default=sorted(df["stance"].dropna().unique()))
q = st.text_input("Search comment title and text") filter_tone = st.multiselect("Filter tone", sorted(df["tone"].dropna().unique()), default=sorted(df["tone"].dropna().unique()))
dff = df[df["stance"].isin(stance)] dff = df[df["stance"].isin(filter_stance) & df["tone"].isin(filter_tone)]
if q:
dff = dff[dff["text"].fillna("").str.contains(q, case=False, regex=False)]
with cex_right: with cex_right:
filter_tone = st.multiselect("Filter tone", sorted(df["tone"].dropna().unique()), default=sorted(df["tone"].dropna().unique())) q = st.text_input("Search comment title and text")
if q:
dff = dff[dff["text"].fillna("").str.contains(q, case=False, regex=False)]
st.text(""); st.text("") st.text(""); st.text("")
st.text("Showing " + str(len(dff))+ " comments",text_alignment="right", width="stretch") st.text("Showing " + str(len(dff))+ " comments",text_alignment="right", width="stretch")