def get_cv_cpv(x: str, percent: float) -> float:
global model_goal
# Get dataset number
dataset_num = get_dataset_num(x)
# Get number of pcs for CPV > 0.8 and CPV > 0.99
if percent == 0.99:
pcs_cpv = df_selection.loc[dataset_num, "Cum. Perc. Var. (0.99)"]
else:
pcs_cpv = df_selection.loc[dataset_num, "Cum. Perc. Var. (0.8)"]
# Get df_results
df = pd.read_csv(x)
idx = df.features_kept == pcs_cpv
try:
return df.loc[idx].cv.values[0]
except:
inputs = Inputs(paths)
inputs.random_seed = 1969
inputs.get_df_split(dataset_num)
pca_model = get_pca_model(inputs)
cluster_model = Clustering(inputs.num_cluster, 100, inputs.random_seed)
cluster_model.fit(pca_model.pcs_train.loc[:, :pcs_cpv - 1])
cluster_prediction = cluster_model.predict(
pca_model.pcs_test.loc[:, :pcs_cpv - 1])
cluster_performances = cluster_model.get_cluster_performances(
inputs.df_test.copy(),
cluster_prediction,
pcs_cpv,
inputs.num_cluster,
model_goal=model_goal)
return variation(cluster_performances)
