First data dump and metadata handling

.gitignore

@@ -1,3 +1,6 @@
+data_very_raw/
+zzz_raman_spectroscopy-main/
+
 # ---> Python
 # Byte-compiled / optimized / DLL files
 __pycache__/

data_raw/metadata.csv

@@ -0,0 +1,29 @@
+file,strain,replica,phase,objective,substrate,laser_power[%],grating,exposition[sec],confocalhigh,accumulations
+A390SampleSpectraLiquid1_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu.txt,A390,1.0,liquid,50,alu,100,1800,20,True,2
+A390SampleSpectraliquid3_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu (2).txt,A390,3.0,liquid,50,alu,100,1800,20,True,2
+A390SampleSpectraliquid3_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu.txt,A390,3.0,liquid,50,alu,100,1800,20,True,2
+A390SampleSpectraSolid2_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu (2).txt,A390,2.0,solid,50,alu,100,1800,20,True,2
+A390SampleSpectraSolid2_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu.txt,A390,2.0,solid,50,alu,100,1800,20,True,2
+A390SampleSpectraSolid3_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu.txt,A390,3.0,solid,50,alu,100,1800,20,True,2
+A390SampleSpectraSolid3_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu_round211 (2).txt,A390,3.0,solid,50,alu,100,1800,20,True,2
+A390SampleSpectraSolid3_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu_round211.txt,A390,3.0,solid,50,alu,100,1800,20,True,2
+CHA0Liquid1_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu.txt,CHA0,1.0,liquid,50,alu,100,1800,20,True,2
+CHA0SampleSpectraLiquid1_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu_round (2).txt,CHA0,1.0,liquid,50,alu,100,1800,20,True,2
+CHA0SampleSpectraLiquid1_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu_round.txt,CHA0,1.0,liquid,50,alu,100,1800,20,True,2
+CHA0SampleSpectraLiquid3_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu.txt,CHA0,3.0,liquid,50,alu,100,1800,20,True,2
+CHA0SampleSpectraLiquid3_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu_round2.txt,CHA0,3.0,liquid,50,alu,100,1800,20,True,2
+CHA0SampleSpectraSolid1_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu_round2 (2).txt,CHA0,1.0,solid,50,alu,100,1800,20,True,2
+CHA0SampleSpectraSolid1_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu_round2.txt,CHA0,1.0,solid,50,alu,100,1800,20,True,2
+CHA0SampleSpectraSolid_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu (2).txt,CHA0,,soli,50,alu,100,1800,20,True,2
+CHA0SampleSpectraSolid_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu(1).txt,CHA0,,soli,50,alu,100,1800,20,True,2
+CHA0SampleSpectraSolid_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu.txt,CHA0,,soli,50,alu,100,1800,20,True,2
+CHA0SampleSpectra_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu.txt,CHA0,,,50,alu,100,1800,20,True,2
+F113SampleSpectraLiquid3_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu (2).txt,F113,3.0,liquid,50,alu,100,1800,20,True,2
+F113SampleSpectraLiquid3_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu.txt,F113,3.0,liquid,50,alu,100,1800,20,True,2
+F113SampleSpectraLiquid3_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu_round2_otherdrop1 (2).txt,F113,3.0,liquid,50,alu,100,1800,20,True,2
+F113SampleSpectraLiquid3_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu_round2_otherdrop1.txt,F113,3.0,liquid,50,alu,100,1800,20,True,2
+F113SampleSpectraLiquid_50x_dried3_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu_round2_otherdrop.txt,F113,,liqui,50,alu,100,1800,20,True,2
+F113SampleSpectraLiquid_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu.txt,F113,,liqui,50,alu,100,1800,20,True,2
+F113SampleSpectraSolid2_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu.txt,F113,2.0,solid,50,alu,100,1800,20,True,2
+F113SampleSpectraSolid2_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu_round2 (2).txt,F113,2.0,solid,50,alu,100,1800,20,True,2
+F113SampleSpectraSolid2_50x_dried_drop_alu_100percent_1800gr_20sec_confocalhigh_2accu_round2.txt,F113,2.0,solid,50,alu,100,1800,20,True,2

data_raw/metadata_aggregator.py

@@ -0,0 +1,21 @@
+import os
+import pandas as pd
+
+
+df = pd.DataFrame([i for i in os.listdir() if i.endswith(".txt")], columns=["file"])
+df["strain"] = df.apply(lambda x: x.file[:4].upper(), axis=1)
+df["replica"] = df.apply(lambda x: x.file.split("_")[0][-1], axis=1)
+df["replica"] = df.apply(lambda x: int(x.replica) if x.replica.isnumeric() else None, axis=1)
+df["phase"] = df.apply(lambda x: x.file.split("_")[0].replace("SampleSpectra", "")[4:-1 if x.replica is not None else None].casefold(), axis=1)
+df["objective"] = df.apply(lambda x: int(x.file.split("_")[1].replace("x", "")), axis=1)
+df["substrate"] = df.apply(lambda x: x.file.split("_")[4].casefold(), axis=1)
+df["laser_power[%]"] = df.apply(lambda x: int(x.file.split("_")[5].replace("percent", "")), axis=1)
+df["grating"] = df.apply(lambda x: int(x.file.split("_")[6].replace("gr", "")), axis=1)
+df["exposition[sec]"] = df.apply(lambda x: int(x.file.split("_")[7].replace("sec", "")), axis=1)
+df["confocalhigh"] = df.apply(lambda x: x.file.split("_")[8] == "confocalhigh", axis=1)
+df["accumulations"] = df.apply(lambda x: int(x.file.split("_")[9].replace("."," ").replace("(", " ").split()[0].replace("accu", "")), axis=1)
+df.set_index("file", inplace=True)
+df.to_csv("metadata.csv")
+
+
+print(df)