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

Added testing section after feature selection.

ml_pipeline
Primoz 2023-04-20 13:29:14 +02:00
parent 259be708aa
commit 865225994b
1 changed files with 29 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
exploration/ml_pipeline.py
View File

@ -20,6 +20,9 @@ import numpy as np
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
import pandas as pd import pandas as pd
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import recall_score, f1_score
nb_dir = os.path.split(os.getcwd())[0] nb_dir = os.path.split(os.getcwd())[0]
if nb_dir not in sys.path: if nb_dir not in sys.path:
sys.path.append(nb_dir) sys.path.append(nb_dir)
@ -34,8 +37,8 @@ index_columns = ["local_segment", "local_segment_label", "local_segment_start_da
df.set_index(index_columns, inplace=True) df.set_index(index_columns, inplace=True)
# Create binary target # Create binary target
# bins = [-1, 0, 4] # bins for stressfulness (0-4) target bins = [-1, 0, 4] # bins for stressfulness (0-4) target
# df['target'], edges = pd.cut(df.target, bins=bins, labels=[0, 1], retbins=True, right=True) #['low', 'medium', 'high'] df['target'], edges = pd.cut(df.target, bins=bins, labels=[0, 1], retbins=True, right=True) #['low', 'medium', 'high']
nan_cols = df.columns[df.isna().any()].tolist() nan_cols = df.columns[df.isna().any()].tolist()
@ -53,20 +56,38 @@ for split in cv.get_splits():
pre.one_hot_encode_train_and_test_sets(categorical_columns) pre.one_hot_encode_train_and_test_sets(categorical_columns)
train_X, train_y, test_X, test_y = pre.get_train_test_sets() train_X, train_y, test_X, test_y = pre.get_train_test_sets()
# train_X = train_X[train_X.columns[:30]]
print(train_X.shape, test_X.shape)
# Predict before feature selection
rfc = RandomForestClassifier(n_estimators=10)
rfc.fit(train_X, train_y)
predictions = rfc.predict(test_X)
print("Recall:", recall_score(test_y, predictions))
print("F1:", f1_score(test_y, predictions))
# Feature selection on train set # Feature selection on train set
# Morda se implementira GroupKfold namesto stratifiedKFold? >>
# >> Tako se bo posamezen pid pojavil ali v test ali v train setu
train_groups, test_groups = cv.get_groups_sets(split) train_groups, test_groups = cv.get_groups_sets(split)
fs = FeatureSelection(train_X, train_y, train_groups) fs = FeatureSelection(train_X, train_y, train_groups)
selected_features = fs.select_features(n_min=20, n_max=50, k=60, selected_features = fs.select_features(n_min=20, n_max=29, k=40,
ml_type="classification_multi", ml_type="classification_bin",
metric="f1", n_tolerance=20) metric="recall", n_tolerance=20)
train_X = train_X[selected_features]
test_X = test_X[selected_features]
print(selected_features) print(selected_features)
print(len(selected_features)) print(len(selected_features))
# Predict after feature selection
rfc = RandomForestClassifier(n_estimators=500)
rfc.fit(train_X, train_y)
predictions = rfc.predict(test_X)
print("Recall:", recall_score(test_y, predictions))
print("F1:", f1_score(test_y, predictions))
break break
# %% # %%