Spaces:
Sleeping
Sleeping
File size: 3,411 Bytes
08c9602 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 |
import time
import pandas as pd
import plotly.express as px
import streamlit as st
# Map the section keys (space‐separated) to the DataFrame column to group by.
SECTION_CONFIG = {
"flex bucket": {
"group_col": "BUCKET",
"drop_percent": 0.10
},
"bidder": {
"group_col": "HB_BIDDER",
"drop_percent": 0.10
},
"device": {
"group_col": "DEVICE",
"drop_percent": 0.10
},
"ad unit": {
"group_col": "AD_UNIT_GROUP",
"drop_percent": 0.10
},
"refresh": {
"group_col": "REFRESH",
"drop_percent": 0.10
},
}
def update_section_generic_drop(key, df, start_times, container, drop_time):
"""
A generic 5‑minute breakdown with drop detection.
'key' can be 'flex_bucket' or 'flex bucket' (we normalize it).
"""
elapsed = time.time() - start_times[key]
mins, secs = divmod(elapsed, 60)
# Standardize column names & build timestamp
df.columns = [c.upper() for c in df.columns]
df = df.sort_values(["EST_HOUR", "EST_MINUTE"])
df["timestamp"] = pd.to_datetime(
df["EST_DATE"].astype(str) + " " +
df["EST_HOUR"].astype(str).str.zfill(2) + ":" +
df["EST_MINUTE"].astype(str).str.zfill(2)
)
df["5MIN"] = df["timestamp"].dt.floor("5T")
# Normalize the lookup key to match SECTION_CONFIG
lookup = key.replace("_", " ").lower()
config = SECTION_CONFIG.get(lookup)
if not config:
st.error(f"No configuration for section '{key}'.")
return
group_col = config["group_col"]
drop_pct = config["drop_percent"]
with container:
st.subheader(f"{lookup.title()} Data")
st.info(f"Query completed in {int(mins)}m {secs:.2f}s")
# Filter to TODAY (uppercase)
today_data = df[df["TIMEFRAME"].str.upper() == "TODAY"]
if today_data.empty:
st.info("No TODAY data for this section.")
return
# Aggregate over 5‑min intervals & plot
agg_today = (
today_data
.groupby(["5MIN", group_col], as_index=False)["CNT"]
.sum()
)
title = f"{lookup.title()} Impressions by Time of Day (5‑min)"
fig = px.line(
agg_today,
x="5MIN",
y="CNT",
color=group_col,
title=title,
labels={"5MIN": "Time", "CNT": "Impressions", group_col: lookup.title()}
)
fig.update_xaxes(tickformat="%I:%M %p")
st.plotly_chart(fig, use_container_width=True)
# Drop detection at the flagged interval
drop_subset = agg_today[agg_today["5MIN"] == drop_time]
flagged = []
if not drop_subset.empty:
avg_cnt = drop_subset["CNT"].mean()
for grp, cnt in drop_subset.groupby(group_col)["CNT"].sum().items():
if cnt <= (1 - drop_pct) * avg_cnt:
flagged.append(grp)
drop_str = drop_time.strftime("%I:%M %p") if drop_time else "N/A"
if flagged:
st.warning(f"{lookup.title()}: At {drop_str}, these groups dropped: {', '.join(flagged)}.")
else:
st.info(f"{lookup.title()}: No significant drop at {drop_str}.")
# Optional raw TODAY data
with st.expander(f"Show Raw TODAY {lookup.title()} Data"):
st.dataframe(today_data)
|