data processing tkt c'est nickel

data/data_loading.py

@@ -1,3 +1,5 @@
+import os
+import numpy as np
 import pandas as pd
 from utils.df_utils import *
 
@@ -39,7 +41,7 @@ def get_raw_measure_with_metadata(file: pd.Series) -> tuple[pd.DataFrame, list[p
     return metadata, sliced_experiments
 
 
-def load_data() -> tuple[pd.DataFrame, list[pd.DataFrame]]:
+def load_raw_data() -> tuple[pd.DataFrame, list[pd.DataFrame]]:
     """
     Load all the available data, slice it into individual measures and give the corresponding metadata
     :return: dataframe containing the metadata with one row per sliced measure
@@ -52,3 +54,18 @@ def load_data() -> tuple[pd.DataFrame, list[pd.DataFrame]]:
         metadata = pd.concat([metadata, temp_metadata])
         sliced_experiments.extend(temp_sliced_experiments)
     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"))
+    return metadata, experiments