junos
/
stress_at_work_analysis
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Small corrections.

master
junos 2023-05-19 03:19:42 +02:00
parent aa13123136
commit aca84b214d
1 changed files with 8 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
exploration/ml_pipeline_classification_with_clustering.py
View File

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