chavalitros
/
IN-P2
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Normalize numerical attributes

This commit is contained in:
coolneng 2020-12-09 21:02:16 +01:00
parent b6b7ffc409
commit e9aeae37cb
Signed by: coolneng
GPG Key ID: 9893DA236405AF57
1 changed files with 16 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
src/P2/preprocessing.py
View File

@ -1,4 +1,5 @@
from pandas import DataFrame, read_csv from pandas import DataFrame, read_csv
from sklearn.preprocessing import normalize
def replace_values(df) -> DataFrame: def replace_values(df) -> DataFrame:
@ -37,7 +38,21 @@ def filter_dataframe(df) -> DataFrame:
return filtered_df return filtered_df
def normalize_numerical_values(df) -> DataFrame:
cols = [
"TOT_HERIDOS_LEVES",
"TOT_HERIDOS_GRAVES",
"TOT_VEHICULOS_IMPLICADOS",
"TOT_MUERTOS",
]
filtered_df = df.filter(items=cols)
normalized_df = normalize(X=filtered_df)
updated_df = df.update(normalized_df)
return updated_df
def parse_data(source, action) -> DataFrame: def parse_data(source, action) -> DataFrame:
df = read_csv(filepath_or_buffer=source, na_values="?") df = read_csv(filepath_or_buffer=source, na_values="?")
processed_df = process_na(df=df, action=action) processed_df = process_na(df=df, action=action)
return processed_df normalized_df = normalize_numerical_values(df=processed_df)
return normalized_df