edufour/RamanClassifier
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Better data processing

Browse Source
This commit is contained in:
edufour
2024-04-16 16:29:34 +02:00
parent 87e1af2ea2
commit 98e51bee46
7 changed files with 12840 additions and 359 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
data/data_loading.py
View File

@@ -1,7 +1,6 @@
import os
import numpy as np
import pandas as pd
from utils.df_utils import *
import os
from utils.df_utils import slice_df
def load_raw_metadata() -> pd.DataFrame:
@@ -56,15 +55,6 @@ def load_raw_data() -> tuple[pd.DataFrame, list[pd.DataFrame]]:
return metadata, sliced_experiments
def data_to_single_df(data: list[pd.DataFrame]) -> pd.DataFrame:
"""
Converts a list of dataframes into a long dataframe. Loses lots of info, to use with care!
:param data: list of dataframes of same length
:return:
"""
return pd.DataFrame(map(lambda x: np.append(x.index.to_numpy(), x["#Intensity"].to_numpy()), data))
def load_data(name: str, path: os.path = os.path.join("data")) -> tuple[pd.DataFrame, pd.DataFrame]:
metadata = pd.read_csv(os.path.join(path, name, "metadata.csv"))
experiments = pd.read_csv(os.path.join(path, name, "experiments.csv"))