Allow parametrizing paths

pulkka/config.py

@@ -0,0 +1,5 @@
+import os
+from pathlib import Path
+
+DATA_DIR = Path(os.environ.get("DATA_DIR", "data"))
+OUT_DIR = Path(os.environ.get("OUT_DIR", "out"))

pulkka/copy_massaged_data.py

@@ -1,13 +1,14 @@
+from pulkka.config import OUT_DIR
 from pulkka.data_ingest import read_data
 
 
 def main():
     df = read_data()
-    df.to_html("out/data.html", index=False)
+    df.to_html(OUT_DIR / "data.html", index=False)
-    df.to_csv("out/data.csv", index=False)
+    df.to_csv(OUT_DIR / "data.csv", index=False)
-    df.to_excel("out/data.xlsx", index=False)
+    df.to_excel(OUT_DIR / "data.xlsx", index=False)
     df.to_json(
-        "out/data.json",
+        OUT_DIR / "data.json",
         orient="records",
         date_format="iso",
         force_ascii=False,

pulkka/data_ingest.py

@@ -3,6 +3,8 @@ import re
 import numpy as np
 import pandas as pd
 
+from pulkka.config import DATA_DIR
+
 COLUMN_MAP = {
     "Missä kaupungissa työpaikkasi pääasiallinen toimisto sijaitsee?": "Kaupunki",
     "Työaika (jos työsuhteessa)": "Työaika",
@@ -61,7 +63,7 @@ def map_ika(d):
 
 def read_data() -> pd.DataFrame:
     df: pd.DataFrame = pd.read_excel(
-        "data/results.xlsx",
+        DATA_DIR / "results.xlsx",
         skiprows=[1],  # Google Sheets exports one empty row
     )
     df.rename(columns=COLUMN_MAP, inplace=True)

pulkka/generate_charts.py

@@ -9,6 +9,7 @@ from pulkka.chart_utils import (
     set_yaxis_cash,
     get_categorical_stats_plot,
 )
+from pulkka.config import OUT_DIR
 from pulkka.data_ingest import read_data
 
 plot_funcs = set()
@@ -56,7 +57,7 @@ def plot_kaupunki_vuositulot(df: DataFrame):
 def main():
     df = read_data()
     plots = [func(df) for func in sorted(plot_funcs, key=lambda f: f.__name__)]
-    bp.output_file("out/charts.html", title="Koodiklinikan Palkkakysely")
+    bp.output_file(OUT_DIR / "charts.html", title="Koodiklinikan Palkkakysely")
     bp.save(bl.grid(plots, ncols=2, sizing_mode="stretch_both"))
 
 

pulkka/generate_profiling.py

@@ -1,3 +1,4 @@
+from pulkka.config import OUT_DIR
 from pulkka.data_ingest import read_data, force_tulot_numeric, force_age_numeric
 from pandas_profiling import ProfileReport
 
@@ -7,7 +8,7 @@ def main():
     df = force_tulot_numeric(df)
     df = force_age_numeric(df)
     profile = ProfileReport(df)
-    profile.to_file("out/profiling_report.html")
+    profile.to_file(OUT_DIR / "profiling_report.html")
 
 
 if __name__ == "__main__":

pulkka/massage_templates.py

@@ -6,6 +6,7 @@ import jinja2
 import numpy
 import pandas
 
+from pulkka.config import OUT_DIR
 from pulkka.data_ingest import read_data
 
 
@@ -20,7 +21,7 @@ def main():
         "df": read_data(),
     }
     for filename in glob.glob("template/*"):
-        out_filename = os.path.join("out", os.path.relpath(filename, "template"))
+        out_filename = OUT_DIR / os.path.relpath(filename, "template")
         with open(filename, "r") as inf:
             tpl: jinja2.Template = env.from_string(inf.read())
             content = tpl.render(data)