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

Better random forests

Browse Source
This commit is contained in:
edufour
2024-04-29 15:30:39 +02:00
parent 0b8f4ddb2e
commit 0cf89d685f
8 changed files with 987 additions and 18796 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
data/data_processing.py
View File

@@ -80,9 +80,26 @@ def categorize_metadata(metadata: pd.DataFrame) -> tuple[pd.DataFrame, pd.DataFr
return truth, encoded
def process_experiments(experiments: pd.DataFrame, baseline_lam=10, baseline_p=1e-2,
smooth_window_length=7, smooth_polyorder=3) -> pd.DataFrame:
def process_experiments(experiments: pd.DataFrame, baseline_lam: int = 10, baseline_p: float = 1e-2,
smooth_window_length: int = 7, smooth_polyorder: int = 3) -> pd.DataFrame:
experiments = adjust_all_baselines(experiments, lam=baseline_lam, p=baseline_p)
experiments = scale_experiments(experiments)
experiments = smooth_experiments(experiments, window_length=smooth_window_length, polyorder=smooth_polyorder)
return experiments
def process_train_test(params: dict, experiments_train: pd.DataFrame, metadata_train: pd.DataFrame, experiments_test: pd.DataFrame = None, metadata_test: pd.DataFrame = None, scale: bool=True) -> tuple[pd.DataFrame, pd.DataFrame]:
processed_train = process_experiments(experiments_train, **params)
X_train = pd.concat([metadata_train, processed_train], axis=1)
if experiments_test is not None:
processed_test = process_experiments(experiments_test, **params)
X_test = pd.concat([metadata_test, processed_test], axis=1)
else:
X_test = None
if scale:
scaler = StandardScaler()
scaler.fit(X_train)
X_train = scaler.transform(X_train)
if X_test is not None:
X_test = scaler.transform(X_test)
return X_train, X_test