Spaces:
Sleeping
Sleeping
File size: 2,052 Bytes
9db6dea 010071f 3651f7b 010071f 3651f7b 1fadf44 3dbe4ef 1fadf44 3dbe4ef 010071f 1fadf44 9db6dea 3dbe4ef 9db6dea 3dbe4ef 9db6dea 3dbe4ef 9db6dea 3dbe4ef a9cd5f0 3dbe4ef |
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 |
# tools/forecaster.py
import pandas as pd
from statsmodels.tsa.arima.model import ARIMA
import plotly.graph_objects as go
def forecast_metric_tool(file_path: str, date_col: str, value_col: str):
"""
Forecast next 3 periods for any numeric metric, and return a textual table.
Saves a date-indexed PNG under /tmp via our safe monkey-patch.
"""
# 1) Load & parse
df = pd.read_csv(file_path)
try:
df[date_col] = pd.to_datetime(df[date_col])
except Exception:
return f"❌ Could not parse '{date_col}' as dates."
# 2) Coerce metric to numeric & drop invalid
df[value_col] = pd.to_numeric(df[value_col], errors="coerce")
df = df.dropna(subset=[date_col, value_col])
if df.empty:
return f"❌ No valid data for '{value_col}'."
# 3) Sort and set index, infer frequency
df = df.sort_values(date_col)
df.set_index(date_col, inplace=True)
freq = pd.infer_freq(df.index)
if freq is None:
# fallback to daily if pandas can't infer
freq = "D"
df = df.asfreq(freq)
# 4) Fit ARIMA
try:
model = ARIMA(df[value_col], order=(1, 1, 1))
model_fit = model.fit()
except Exception as e:
return f"❌ ARIMA fitting failed: {e}"
# 5) Get a proper date-indexed forecast
fc_res = model_fit.get_forecast(steps=3)
forecast = fc_res.predicted_mean # a pd.Series with a DatetimeIndex
# 6) Plot historical + forecast
fig = go.Figure()
fig.add_scatter(
x=df.index, y=df[value_col],
mode="lines", name=value_col
)
fig.add_scatter(
x=forecast.index, y=forecast,
mode="lines+markers", name="Forecast"
)
fig.update_layout(
title=f"{value_col} Forecast",
xaxis_title=str(date_col),
yaxis_title=str(value_col),
template="plotly_dark"
)
fig.write_image("forecast_plot.png")
# 7) Return the forecast table as text
tbl = forecast.to_frame(name="Forecast")
return tbl.to_string()
|