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

data processing tkt c'est nickel

Browse Source
This commit is contained in:
edufour
2024-03-13 14:13:51 +01:00
parent 66c6e6c931
commit 87e1af2ea2
6 changed files with 477 additions and 145 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
data_raw/metadata_aggregator.py
View File

@@ -6,7 +6,8 @@ df = pd.DataFrame([i for i in os.listdir() if i.endswith(".txt")], columns=["fil
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["phase"] = df.apply(lambda x: x.file.split("_")[0].replace("SampleSpectra", "")[4:].casefold(), axis=1)
df["phase"] = df.apply(lambda x: x.phase if pd.isnull(x.replica) else x.phase[:-1], 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)