From 496541e477d9832426f3c6b04808d89f6ec1a8b6 Mon Sep 17 00:00:00 2001 From: Aarni Koskela Date: Fri, 19 Feb 2021 16:27:58 +0200 Subject: [PATCH] Use forcibly numeric money for profile report --- data_ingest.py | 6 ++++++ generate_profiling.py | 3 ++- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/data_ingest.py b/data_ingest.py index 5ae4db7..9cf7da5 100644 --- a/data_ingest.py +++ b/data_ingest.py @@ -87,6 +87,12 @@ def read_data() -> pd.DataFrame: return df +def force_tulot_numeric(df): + df["Kuukausipalkka"] = pd.to_numeric(df["Kuukausipalkka"], errors="coerce") + df["Vuositulot"] = pd.to_numeric(df["Vuositulot"], errors="coerce") + return df + + def main(): pd.set_option("display.max_column", None) pd.set_option("display.max_rows", None) diff --git a/generate_profiling.py b/generate_profiling.py index 406dcaa..a751276 100644 --- a/generate_profiling.py +++ b/generate_profiling.py @@ -1,9 +1,10 @@ -from data_ingest import read_data +from data_ingest import read_data, force_tulot_numeric from pandas_profiling import ProfileReport def main(): df = read_data() + df = force_tulot_numeric(df) profile = ProfileReport(df) profile.to_file("out/profiling_report.html")