Small corrections.

exploration/ml_pipeline_classification_with_clustering.py

@@ -25,9 +25,6 @@ from sklearn.model_selection import LeaveOneGroupOut, StratifiedKFold, cross_val
 
 from machine_learning.classification_models import ClassificationModels
 
-# %% [markdown]
-# # RAPIDS models
-
 # %%
 # ## Set script's parameters
 N_CLUSTERS = 4  # Number of clusters (could be regarded as a hyperparameter)
@@ -75,8 +72,10 @@ print("BINS: " + str(BINS))
 model_input[CLUST_COL].describe()
 
 
-# %% jupyter={"source_hidden": true}
+# %%
+model_input["target"].value_counts()
 
+# %% jupyter={"source_hidden": true}
 # Filter-out outlier rows by clust_col
 # model_input = model_input[(np.abs(stats.zscore(model_input[clust_col])) < 3)]
 
@@ -92,6 +91,9 @@ uniq["cluster"] = km
 
 model_input = model_input.merge(uniq[["pid", "cluster"]])
 
+# %%
+model_input[["cluster", "target"]].value_counts().sort_index()
+
 # %% jupyter={"source_hidden": true}
 model_input.set_index(index_columns, inplace=True)
 
@@ -107,7 +109,7 @@ for k in range(N_CLUSTERS):
         model_input_subset.loc[:, "target"],
         bins=BINS,
         labels=["low", "high"],
-        right=False,
+        right=True,
     )  # ['low', 'medium', 'high']
     model_input_subset["target"].value_counts()
     # model_input_subset = model_input_subset[model_input_subset["target"] != "medium"]
@@ -115,7 +117,7 @@ for k in range(N_CLUSTERS):
         model_input_subset["target"].astype(str).apply(lambda x: 0 if x == "low" else 1)
     )
 
-    model_input_subset["target"].value_counts()
+    print(model_input_subset["target"].value_counts())
 
     if CV_METHOD == "half_logo":
         model_input_subset["pid_index"] = model_input_subset.groupby("pid").cumcount()