stress_at_work_analysis/machine_learning/helper.py

58 lines
1.5 KiB
Python

from pathlib import Path
import pandas as pd
def safe_outer_merge_on_index(left: pd.DataFrame, right: pd.DataFrame) -> pd.DataFrame:
if left.empty:
return right
elif right.empty:
return left
else:
return pd.merge(
left,
right,
how="outer",
left_index=True,
right_index=True,
validate="one_to_one",
)
def to_csv_with_settings(
df: pd.DataFrame, folder: Path, filename_prefix: str, data_type: str
) -> None:
full_path = construct_full_path(folder, filename_prefix, data_type)
df.to_csv(
path_or_buf=full_path,
sep=",",
na_rep="NA",
header=True,
index=True,
encoding="utf-8",
)
print("Exported the dataframe to " + str(full_path))
def read_csv_with_settings(
folder: Path, filename_prefix: str, data_type: str, grouping_variable: list
) -> pd.DataFrame:
full_path = construct_full_path(folder, filename_prefix, data_type)
return pd.read_csv(
filepath_or_buffer=full_path,
sep=",",
header=0,
na_values="NA",
encoding="utf-8",
index_col=(["participant_id"] + grouping_variable),
parse_dates=True,
infer_datetime_format=True,
cache_dates=True,
)
def construct_full_path(folder: Path, filename_prefix: str, data_type: str) -> Path:
export_filename = filename_prefix + "_" + data_type + ".csv"
full_path = folder / export_filename
return full_path