stress_at_work_analysis/exploration/ml_pipeline_classification.py

# ---
# jupyter:
#   jupytext:
#     formats: ipynb,py:percent
#     text_representation:
#       extension: .py
#       format_name: percent
#       format_version: '1.3'
#       jupytext_version: 1.13.0
#   kernelspec:
#     display_name: straw2analysis
#     language: python
#     name: straw2analysis
# ---

# %% jupyter={"source_hidden": true}
# %matplotlib inline
import datetime
import importlib
import os
import sys

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns

from sklearn import linear_model, svm, naive_bayes, neighbors, tree, ensemble 
from sklearn.model_selection import LeaveOneGroupOut, cross_validate
from sklearn.dummy import DummyClassifier
from sklearn.impute import SimpleImputer

from lightgbm import LGBMClassifier
import xgboost as xg
from IPython.core.interactiveshell import InteractiveShell
InteractiveShell.ast_node_interactivity = "all"

nb_dir = os.path.split(os.getcwd())[0]
if nb_dir not in sys.path:
    sys.path.append(nb_dir)

import machine_learning.labels
import machine_learning.model

# %% [markdown]
# # RAPIDS models

# %% [markdown]
# ## Set script's parameters
cv_method_str = 'logo' # logo, halflogo, 5kfold # Cross-validation method (could be regarded as a hyperparameter)
n_sl = 1 # Number of largest/smallest accuracies (of particular CV) outputs

# %% jupyter={"source_hidden": true}
model_input = pd.read_csv("../data/intradaily_30_min_all_targets/input_JCQ_job_demand_mean.csv")

# %% jupyter={"source_hidden": true}
index_columns = ["local_segment", "local_segment_label", "local_segment_start_datetime", "local_segment_end_datetime"]
model_input.set_index(index_columns, inplace=True)

# %% jupyter={"source_hidden": true}
bins = [-10, -1, 1, 10] # bins for z-scored targets
model_input['target'], edges = pd.cut(model_input.target, bins=bins, labels=['low', 'medium', 'high'], retbins=True, right=True) #['low', 'medium', 'high']
model_input['target'].value_counts(), edges
model_input = model_input[model_input['target'] != "medium"]
model_input['target'] = model_input['target'].astype(str).apply(lambda x: 0 if x == "low" else 1)

model_input['target'].value_counts()

if cv_method_str == 'halflogo':
    model_input['pid_index'] = model_input.groupby('pid').cumcount()
    model_input['pid_count'] = model_input.groupby('pid')['pid'].transform('count')

    model_input["pid_index"] = (model_input['pid_index'] / model_input['pid_count'] + 1).round()
    model_input["pid_half"] = model_input["pid"] + "_" +  model_input["pid_index"].astype(int).astype(str)

    data_x, data_y, data_groups = model_input.drop(["target", "pid", "pid_index", "pid_half"], axis=1), model_input["target"], model_input["pid_half"]
else:
    data_x, data_y, data_groups = model_input.drop(["target", "pid"], axis=1), model_input["target"], model_input["pid"]


# %% jupyter={"source_hidden": true}
categorical_feature_colnames = ["gender", "startlanguage"]
additional_categorical_features = [col for col in data_x.columns if "mostcommonactivity" in col or "homelabel" in col]
categorical_feature_colnames += additional_categorical_features

categorical_features = data_x[categorical_feature_colnames].copy()
mode_categorical_features = categorical_features.mode().iloc[0]

# fillna with mode
categorical_features = categorical_features.fillna(mode_categorical_features)

# one-hot encoding
categorical_features = categorical_features.apply(lambda col: col.astype("category"))
if not categorical_features.empty:
    categorical_features = pd.get_dummies(categorical_features)

numerical_features = data_x.drop(categorical_feature_colnames, axis=1)
train_x = pd.concat([numerical_features, categorical_features], axis=1)
train_x.dtypes

# %% jupyter={"source_hidden": true}
cv_method = None # Defaults to 5 k-folds in cross_validate method
if cv_method_str == 'logo' or cv_method_str == 'half_logo':
    cv_method = LeaveOneGroupOut()
    cv_method.get_n_splits(
        train_x,
        data_y,
        groups=data_groups,
    )

# %% jupyter={"source_hidden": true}
imputer = SimpleImputer(missing_values=np.nan, strategy='median')

# %% [markdown]
# ### Baseline: Dummy Classifier (most frequent)
dummy_class = DummyClassifier(strategy="most_frequent")

# %% jupyter={"source_hidden": true}
dummy_classifier = cross_validate(
    dummy_class,
    X=imputer.fit_transform(train_x),
    y=data_y,
    groups=data_groups,
    cv=cv_method,
    n_jobs=-1,
    error_score='raise',
    scoring=('accuracy', 'average_precision', 'recall', 'f1')
)
# %% jupyter={"source_hidden": true}
print("Acc", np.mean(dummy_classifier['test_accuracy']))
print("Precision", np.mean(dummy_classifier['test_average_precision']))
print("Recall", np.mean(dummy_classifier['test_recall']))
print("F1", np.mean(dummy_classifier['test_f1']))
print(f"Largest {n_sl} ACC:", np.sort(-np.partition(-dummy_classifier['test_accuracy'], n_sl)[:n_sl])[::-1])
print(f"Smallest {n_sl} ACC:", np.sort(np.partition(dummy_classifier['test_accuracy'], n_sl)[:n_sl]))

# %% [markdown]
# ### Logistic Regression

# %% jupyter={"source_hidden": true}
logistic_regression = linear_model.LogisticRegression()

# %% jupyter={"source_hidden": true}
log_reg_scores = cross_validate(
    logistic_regression,
    X=imputer.fit_transform(train_x),
    y=data_y,
    groups=data_groups,
    cv=cv_method,
    n_jobs=-1,
    scoring=('accuracy', 'precision', 'recall', 'f1')
)
# %% jupyter={"source_hidden": true}
print("Acc", np.mean(log_reg_scores['test_accuracy']))
print("Precision", np.mean(log_reg_scores['test_precision']))
print("Recall", np.mean(log_reg_scores['test_recall']))
print("F1", np.mean(log_reg_scores['test_f1']))
print(f"Largest {n_sl} ACC:", np.sort(-np.partition(-log_reg_scores['test_accuracy'], n_sl)[:n_sl])[::-1])
print(f"Smallest {n_sl} ACC:", np.sort(np.partition(log_reg_scores['test_accuracy'], n_sl)[:n_sl]))

# %% [markdown]
# ### Support Vector Machine

# %% jupyter={"source_hidden": true}
svc = svm.SVC()

# %% jupyter={"source_hidden": true}
svc_scores = cross_validate(
    svc,
    X=imputer.fit_transform(train_x),
    y=data_y,
    groups=data_groups,
    cv=cv_method,
    n_jobs=-1,
    scoring=('accuracy', 'precision', 'recall', 'f1')
)
# %% jupyter={"source_hidden": true}
print("Acc", np.mean(svc_scores['test_accuracy']))
print("Precision", np.mean(svc_scores['test_precision']))
print("Recall", np.mean(svc_scores['test_recall']))
print("F1", np.mean(svc_scores['test_f1']))
print(f"Largest {n_sl} ACC:", np.sort(-np.partition(-svc_scores['test_accuracy'], n_sl)[:n_sl])[::-1])
print(f"Smallest {n_sl} ACC:", np.sort(np.partition(svc_scores['test_accuracy'], n_sl)[:n_sl]))

# %% [markdown]
# ### Gaussian Naive Bayes

# %% jupyter={"source_hidden": true}
gaussian_nb = naive_bayes.GaussianNB()

# %% jupyter={"source_hidden": true}
gaussian_nb_scores = cross_validate(
    gaussian_nb,
    X=imputer.fit_transform(train_x),
    y=data_y,
    groups=data_groups,
    cv=cv_method,
    n_jobs=-1,
    error_score='raise',
    scoring=('accuracy', 'precision', 'recall', 'f1')
)
# %% jupyter={"source_hidden": true}
print("Acc", np.mean(gaussian_nb_scores['test_accuracy']))
print("Precision", np.mean(gaussian_nb_scores['test_precision']))
print("Recall", np.mean(gaussian_nb_scores['test_recall']))
print("F1", np.mean(gaussian_nb_scores['test_f1']))
print(f"Largest {n_sl} ACC:", np.sort(-np.partition(-gaussian_nb_scores['test_accuracy'], n_sl)[:n_sl])[::-1])
print(f"Smallest {n_sl} ACC:", np.sort(np.partition(gaussian_nb_scores['test_accuracy'], n_sl)[:n_sl]))

# %% [markdown]
# ### Stochastic Gradient Descent Classifier

# %% jupyter={"source_hidden": true}
sgdc = linear_model.SGDClassifier()

# %% jupyter={"source_hidden": true}
sgdc_scores = cross_validate(
    sgdc,
    X=imputer.fit_transform(train_x),
    y=data_y,
    groups=data_groups,
    cv=cv_method,
    n_jobs=-1,
    error_score='raise',
    scoring=('accuracy', 'precision', 'recall', 'f1')
)
# %% jupyter={"source_hidden": true}
print("Acc", np.mean(sgdc_scores['test_accuracy']))
print("Precision", np.mean(sgdc_scores['test_precision']))
print("Recall", np.mean(sgdc_scores['test_recall']))
print("F1", np.mean(sgdc_scores['test_f1']))
print(f"Largest {n_sl} ACC:", np.sort(-np.partition(-sgdc_scores['test_accuracy'], n_sl)[:n_sl])[::-1])
print(f"Smallest {n_sl} ACC:", np.sort(np.partition(sgdc_scores['test_accuracy'], n_sl)[:n_sl]))

# %% [markdown]
# ### K-nearest neighbors

# %% jupyter={"source_hidden": true}
knn = neighbors.KNeighborsClassifier()

# %% jupyter={"source_hidden": true}
knn_scores = cross_validate(
    knn,
    X=imputer.fit_transform(train_x),
    y=data_y,
    groups=data_groups,
    cv=cv_method,
    n_jobs=-1,
    error_score='raise',
    scoring=('accuracy', 'precision', 'recall', 'f1')
)
# %% jupyter={"source_hidden": true}
print("Acc", np.mean(knn_scores['test_accuracy']))
print("Precision", np.mean(knn_scores['test_precision']))
print("Recall", np.mean(knn_scores['test_recall']))
print("F1", np.mean(knn_scores['test_f1']))
print(f"Largest {n_sl} ACC:", np.sort(-np.partition(-knn_scores['test_accuracy'], n_sl)[:n_sl])[::-1])
print(f"Smallest {n_sl} ACC:", np.sort(np.partition(knn_scores['test_accuracy'], n_sl)[:n_sl]))

# %% [markdown]
# ### Decision Tree

# %% jupyter={"source_hidden": true}
dtree = tree.DecisionTreeClassifier()

# %% jupyter={"source_hidden": true}
dtree_scores = cross_validate(
    dtree,
    X=imputer.fit_transform(train_x),
    y=data_y,
    groups=data_groups,
    cv=cv_method,
    n_jobs=-1,
    error_score='raise',
    scoring=('accuracy', 'precision', 'recall', 'f1')
)
# %% jupyter={"source_hidden": true}
print("Acc", np.mean(dtree_scores['test_accuracy']))
print("Precision", np.mean(dtree_scores['test_precision']))
print("Recall", np.mean(dtree_scores['test_recall']))
print("F1", np.mean(dtree_scores['test_f1']))
print(f"Largest {n_sl} ACC:", np.sort(-np.partition(-dtree_scores['test_accuracy'], n_sl)[:n_sl])[::-1])
print(f"Smallest {n_sl} ACC:", np.sort(np.partition(dtree_scores['test_accuracy'], n_sl)[:n_sl]))

# %% [markdown]
# ### Random Forest Classifier

# %% jupyter={"source_hidden": true}
rfc = ensemble.RandomForestClassifier()

# %% jupyter={"source_hidden": true}
rfc_scores = cross_validate(
    rfc,
    X=imputer.fit_transform(train_x),
    y=data_y,
    groups=data_groups,
    cv=cv_method,
    n_jobs=-1,
    error_score='raise',
    scoring=('accuracy', 'precision', 'recall', 'f1')
)
# %% jupyter={"source_hidden": true}
print("Acc", np.mean(rfc_scores['test_accuracy']))
print("Precision", np.mean(rfc_scores['test_precision']))
print("Recall", np.mean(rfc_scores['test_recall']))
print("F1", np.mean(rfc_scores['test_f1']))
print(f"Largest {n_sl} ACC:", np.sort(-np.partition(-rfc_scores['test_accuracy'], n_sl)[:n_sl])[::-1])
print(f"Smallest {n_sl} ACC:", np.sort(np.partition(rfc_scores['test_accuracy'], n_sl)[:n_sl]))

# %% [markdown]
# ### Gradient Boosting Classifier

# %% jupyter={"source_hidden": true}
gbc = ensemble.GradientBoostingClassifier()

# %% jupyter={"source_hidden": true}
gbc_scores = cross_validate(
    gbc,
    X=imputer.fit_transform(train_x),
    y=data_y,
    groups=data_groups,
    cv=cv_method,
    n_jobs=-1,
    error_score='raise',
    scoring=('accuracy', 'precision', 'recall', 'f1')
)
# %% jupyter={"source_hidden": true}
print("Acc", np.mean(gbc_scores['test_accuracy']))
print("Precision", np.mean(gbc_scores['test_precision']))
print("Recall", np.mean(gbc_scores['test_recall']))
print("F1", np.mean(gbc_scores['test_f1']))
print(f"Largest {n_sl} ACC:", np.sort(-np.partition(-gbc_scores['test_accuracy'], n_sl)[:n_sl])[::-1])
print(f"Smallest {n_sl} ACC:", np.sort(np.partition(gbc_scores['test_accuracy'], n_sl)[:n_sl]))

# %% [markdown]
# ### LGBM Classifier

# %% jupyter={"source_hidden": true}
lgbm = LGBMClassifier()

# %% jupyter={"source_hidden": true}
lgbm_scores = cross_validate(
    lgbm,
    X=imputer.fit_transform(train_x),
    y=data_y,
    groups=data_groups,
    cv=cv_method,
    n_jobs=-1,
    error_score='raise',
    scoring=('accuracy', 'precision', 'recall', 'f1')
)
# %% jupyter={"source_hidden": true}
print("Acc", np.mean(lgbm_scores['test_accuracy']))
print("Precision", np.mean(lgbm_scores['test_precision']))
print("Recall", np.mean(lgbm_scores['test_recall']))
print("F1", np.mean(lgbm_scores['test_f1']))
print(f"Largest {n_sl} ACC:", np.sort(-np.partition(-lgbm_scores['test_accuracy'], n_sl)[:n_sl])[::-1])
print(f"Smallest {n_sl} ACC:", np.sort(np.partition(lgbm_scores['test_accuracy'], n_sl)[:n_sl]))

# %% [markdown]
# ### XGBoost Classifier

# %% jupyter={"source_hidden": true}
xgb_classifier = xg.sklearn.XGBClassifier()

# %% jupyter={"source_hidden": true}
xgb_classifier_scores = cross_validate(
    xgb_classifier,
    X=imputer.fit_transform(train_x),
    y=data_y,
    groups=data_groups,
    cv=cv_method,
    n_jobs=-1,
    error_score='raise',
    scoring=('accuracy', 'precision', 'recall', 'f1')
)
# %% jupyter={"source_hidden": true}
print("Acc", np.mean(xgb_classifier_scores['test_accuracy']))
print("Precision", np.mean(xgb_classifier_scores['test_precision']))
print("Recall", np.mean(xgb_classifier_scores['test_recall']))
print("F1", np.mean(xgb_classifier_scores['test_f1']))
print(f"Largest {n_sl} ACC:", np.sort(-np.partition(-xgb_classifier_scores['test_accuracy'], n_sl)[:n_sl])[::-1])
print(f"Smallest {n_sl} ACC:", np.sort(np.partition(xgb_classifier_scores['test_accuracy'], n_sl)[:n_sl]))