diff --git a/exploration/ml_pipeline_classification_with_clustering.py b/exploration/ml_pipeline_classification_with_clustering.py index 66fd597..d4c7f54 100644 --- a/exploration/ml_pipeline_classification_with_clustering.py +++ b/exploration/ml_pipeline_classification_with_clustering.py @@ -6,7 +6,7 @@ # extension: .py # format_name: percent # format_version: '1.3' -# jupytext_version: 1.13.0 +# jupytext_version: 1.14.5 # kernelspec: # display_name: straw2analysis # language: python @@ -15,57 +15,45 @@ # %% jupyter={"source_hidden": true} # %matplotlib inline -import datetime -import importlib import os import sys -import numpy as np import matplotlib.pyplot as plt +import numpy as np import pandas as pd -import seaborn as sns -from scipy import stats - -from sklearn.model_selection import LeaveOneGroupOut, cross_validate -from sklearn.impute import SimpleImputer - -from sklearn.dummy import DummyClassifier -from sklearn import linear_model, svm, naive_bayes, neighbors, tree, ensemble -import xgboost as xg - from sklearn.cluster import KMeans +from sklearn.impute import SimpleImputer +from sklearn.model_selection import LeaveOneGroupOut, StratifiedKFold, cross_validate -from IPython.core.interactiveshell import InteractiveShell -InteractiveShell.ast_node_interactivity = "all" +from machine_learning.classification_models import ClassificationModels 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 -from machine_learning.classification_models import ClassificationModels # %% [markdown] # # RAPIDS models -# %% [markdown] +# %% # ## Set script's parameters -n_clusters = 4 # Number of clusters (could be regarded as a hyperparameter) -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 +N_CLUSTERS = 4 # Number of clusters (could be regarded as a hyperparameter) +CV_METHOD = "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/30min_all_target_inputs/input_JCQ_job_demand_mean.csv") -index_columns = ["local_segment", "local_segment_label", "local_segment_start_datetime", "local_segment_end_datetime"] +model_input = pd.read_csv( + "E:/STRAWresults/20230415/30_minutes_before/input_PANAS_negative_affect_mean.csv" +) +index_columns = [ + "local_segment", + "local_segment_label", + "local_segment_start_datetime", + "local_segment_end_datetime", +] -clust_col = model_input.set_index(index_columns).var().idxmax() # age is a col with the highest variance - -model_input.columns[list(model_input.columns).index('age'):-1] - -lime_cols = [col for col in model_input if col.startswith('limesurvey')] -lime_cols -lime_col = 'limesurvey_demand_control_ratio_quartile' +lime_col = "limesurvey_demand_control_ratio_quartile" clust_col = lime_col model_input[clust_col].describe() @@ -73,21 +61,20 @@ model_input[clust_col].describe() # %% jupyter={"source_hidden": true} -# Filter-out outlier rows by clust_col -#model_input = model_input[(np.abs(stats.zscore(model_input[clust_col])) < 3)] +# Filter-out outlier rows by clust_col +# model_input = model_input[(np.abs(stats.zscore(model_input[clust_col])) < 3)] -uniq = model_input[[clust_col, 'pid']].drop_duplicates().reset_index(drop=True) +uniq = model_input[[clust_col, "pid"]].drop_duplicates().reset_index(drop=True) uniq = uniq.dropna() -plt.bar(uniq['pid'], uniq[clust_col]) +plt.bar(uniq["pid"], uniq[clust_col]) # %% jupyter={"source_hidden": true} # Get clusters by cluster col & and merge the clusters to main df -km = KMeans(n_clusters=n_clusters).fit_predict(uniq.set_index('pid')) +km = KMeans(n_clusters=N_CLUSTERS).fit_predict(uniq.set_index("pid")) np.unique(km, return_counts=True) -uniq['cluster'] = km -uniq +uniq["cluster"] = km -model_input = model_input.merge(uniq[['pid', 'cluster']]) +model_input = model_input.merge(uniq[["pid", "cluster"]]) # %% jupyter={"source_hidden": true} model_input.set_index(index_columns, inplace=True) @@ -98,31 +85,57 @@ cm = ClassificationModels() cmodels = cm.get_cmodels() # %% jupyter={"source_hidden": true} -for k in range(n_clusters): +for k in range(N_CLUSTERS): model_input_subset = model_input[model_input["cluster"] == k].copy() - bins = [-10, -1, 1, 10] # bins for z-scored targets - model_input_subset.loc[:, 'target'] = \ - pd.cut(model_input_subset.loc[:, 'target'], bins=bins, labels=['low', 'medium', 'high'], right=False) #['low', 'medium', 'high'] - model_input_subset['target'].value_counts() - model_input_subset = model_input_subset[model_input_subset['target'] != "medium"] - model_input_subset['target'] = model_input_subset['target'].astype(str).apply(lambda x: 0 if x == "low" else 1) + bins = [-10, -1, 1, 10] # bins for z-scored targets + model_input_subset.loc[:, "target"] = pd.cut( + model_input_subset.loc[:, "target"], + bins=bins, + labels=["low", "medium", "high"], + right=False, + ) # ['low', 'medium', 'high'] + model_input_subset["target"].value_counts() + model_input_subset = model_input_subset[model_input_subset["target"] != "medium"] + model_input_subset["target"] = ( + model_input_subset["target"].astype(str).apply(lambda x: 0 if x == "low" else 1) + ) - model_input_subset['target'].value_counts() - - if cv_method_str == 'half_logo': - model_input_subset['pid_index'] = model_input_subset.groupby('pid').cumcount() - model_input_subset['pid_count'] = model_input_subset.groupby('pid')['pid'].transform('count') + model_input_subset["target"].value_counts() - model_input_subset["pid_index"] = (model_input_subset['pid_index'] / model_input_subset['pid_count'] + 1).round() - model_input_subset["pid_half"] = model_input_subset["pid"] + "_" + model_input_subset["pid_index"].astype(int).astype(str) + if CV_METHOD == "half_logo": + model_input_subset["pid_index"] = model_input_subset.groupby("pid").cumcount() + model_input_subset["pid_count"] = model_input_subset.groupby("pid")[ + "pid" + ].transform("count") - data_x, data_y, data_groups = model_input_subset.drop(["target", "pid", "pid_index", "pid_half"], axis=1), model_input_subset["target"], model_input_subset["pid_half"] + model_input_subset["pid_index"] = ( + model_input_subset["pid_index"] / model_input_subset["pid_count"] + 1 + ).round() + model_input_subset["pid_half"] = ( + model_input_subset["pid"] + + "_" + + model_input_subset["pid_index"].astype(int).astype(str) + ) + + data_x, data_y, data_groups = ( + model_input_subset.drop(["target", "pid", "pid_index", "pid_half"], axis=1), + model_input_subset["target"], + model_input_subset["pid_half"], + ) else: - data_x, data_y, data_groups = model_input_subset.drop(["target", "pid"], axis=1), model_input_subset["target"], model_input_subset["pid"] + data_x, data_y, data_groups = ( + model_input_subset.drop(["target", "pid"], axis=1), + model_input_subset["target"], + model_input_subset["pid"], + ) # Treat categorical features categorical_feature_colnames = ["gender", "startlanguage"] - additional_categorical_features = [col for col in data_x.columns if "mostcommonactivity" in col or "homelabel" in col] + 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() @@ -132,7 +145,9 @@ for k in range(n_clusters): categorical_features = categorical_features.fillna(mode_categorical_features) # one-hot encoding - categorical_features = categorical_features.apply(lambda col: col.astype("category")) + categorical_features = categorical_features.apply( + lambda col: col.astype("category") + ) if not categorical_features.empty: categorical_features = pd.get_dummies(categorical_features) @@ -140,8 +155,10 @@ for k in range(n_clusters): train_x = pd.concat([numerical_features, categorical_features], axis=1) # Establish cv method - cv_method = StratifiedKFold(n_splits=5, shuffle=True) # Defaults to 5 k-folds in cross_validate method - if cv_method_str == 'logo' or cv_method_str == 'half_logo': + cv_method = StratifiedKFold( + n_splits=5, shuffle=True + ) # Defaults to 5 k-folds in cross_validate method + if CV_METHOD == "logo" or CV_METHOD == "half_logo": cv_method = LeaveOneGroupOut() cv_method.get_n_splits( train_x, @@ -149,36 +166,41 @@ for k in range(n_clusters): groups=data_groups, ) - imputer = SimpleImputer(missing_values=np.nan, strategy='median') + imputer = SimpleImputer(missing_values=np.nan, strategy="median") for model_title, model in cmodels.items(): - classifier = cross_validate( - model['model'], + model["model"], 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') + error_score="raise", + scoring=("accuracy", "precision", "recall", "f1"), ) - + print("\n-------------------------------------\n") print("Current cluster:", k, end="\n") print("Current model:", model_title, end="\n") - print("Acc", np.mean(classifier['test_accuracy'])) - print("Precision", np.mean(classifier['test_precision'])) - print("Recall", np.mean(classifier['test_recall'])) - print("F1", np.mean(classifier['test_f1'])) - print(f"Largest {n_sl} ACC:", np.sort(-np.partition(-classifier['test_accuracy'], n_sl)[:n_sl])[::-1]) - print(f"Smallest {n_sl} ACC:", np.sort(np.partition(classifier['test_accuracy'], n_sl)[:n_sl])) - - cmodels[model_title]['metrics'][0] += np.mean(classifier['test_accuracy']) - cmodels[model_title]['metrics'][1] += np.mean(classifier['test_precision']) - cmodels[model_title]['metrics'][2] += np.mean(classifier['test_recall']) - cmodels[model_title]['metrics'][3] += np.mean(classifier['test_f1']) + print("Acc", np.mean(classifier["test_accuracy"])) + print("Precision", np.mean(classifier["test_precision"])) + print("Recall", np.mean(classifier["test_recall"])) + print("F1", np.mean(classifier["test_f1"])) + print( + f"Largest {N_SL} ACC:", + np.sort(-np.partition(-classifier["test_accuracy"], N_SL)[:N_SL])[::-1], + ) + print( + f"Smallest {N_SL} ACC:", + np.sort(np.partition(classifier["test_accuracy"], N_SL)[:N_SL]), + ) + + cmodels[model_title]["metrics"][0] += np.mean(classifier["test_accuracy"]) + cmodels[model_title]["metrics"][1] += np.mean(classifier["test_precision"]) + cmodels[model_title]["metrics"][2] += np.mean(classifier["test_recall"]) + cmodels[model_title]["metrics"][3] += np.mean(classifier["test_f1"]) # %% jupyter={"source_hidden": true} # Get overall results -cm.get_total_models_scores(n_clusters=n_clusters) +scores = cm.get_total_models_scores(n_clusters=N_CLUSTERS) diff --git a/machine_learning/classification_models.py b/machine_learning/classification_models.py index 82c26b8..852a36c 100644 --- a/machine_learning/classification_models.py +++ b/machine_learning/classification_models.py @@ -1,71 +1,95 @@ -from sklearn.dummy import DummyClassifier -from sklearn import linear_model, svm, naive_bayes, neighbors, tree, ensemble +import pandas as pd +import xgboost as xg from lightgbm import LGBMClassifier -import xgboost as xg +from sklearn import ensemble, linear_model, naive_bayes, neighbors, svm, tree +from sklearn.dummy import DummyClassifier -class ClassificationModels(): - + +class ClassificationModels: def __init__(self): self.cmodels = self.init_classification_models() - + def get_cmodels(self): return self.cmodels def init_classification_models(self): cmodels = { - 'dummy_classifier': { - 'model': DummyClassifier(strategy="most_frequent"), - 'metrics': [0, 0, 0, 0] + "dummy_classifier": { + "model": DummyClassifier(strategy="most_frequent"), + "metrics": [0, 0, 0, 0], }, - 'logistic_regression': { - 'model': linear_model.LogisticRegression(max_iter=1000), - 'metrics': [0, 0, 0, 0] + "logistic_regression": { + "model": linear_model.LogisticRegression(max_iter=1000), + "metrics": [0, 0, 0, 0], }, - 'support_vector_machine': { - 'model': svm.SVC(), - 'metrics': [0, 0, 0, 0] + "support_vector_machine": {"model": svm.SVC(), "metrics": [0, 0, 0, 0]}, + "gaussian_naive_bayes": { + "model": naive_bayes.GaussianNB(), + "metrics": [0, 0, 0, 0], }, - 'gaussian_naive_bayes': { - 'model': naive_bayes.GaussianNB(), - 'metrics': [0, 0, 0, 0] + "stochastic_gradient_descent_classifier": { + "model": linear_model.SGDClassifier(), + "metrics": [0, 0, 0, 0], }, - 'stochastic_gradient_descent_classifier': { - 'model': linear_model.SGDClassifier(), - 'metrics': [0, 0, 0, 0] + "knn": {"model": neighbors.KNeighborsClassifier(), "metrics": [0, 0, 0, 0]}, + "decision_tree": { + "model": tree.DecisionTreeClassifier(), + "metrics": [0, 0, 0, 0], }, - 'knn': { - 'model': neighbors.KNeighborsClassifier(), - 'metrics': [0, 0, 0, 0] + "random_forest_classifier": { + "model": ensemble.RandomForestClassifier(), + "metrics": [0, 0, 0, 0], }, - 'decision_tree': { - 'model': tree.DecisionTreeClassifier(), - 'metrics': [0, 0, 0, 0] + "gradient_boosting_classifier": { + "model": ensemble.GradientBoostingClassifier(), + "metrics": [0, 0, 0, 0], }, - 'random_forest_classifier': { - 'model': ensemble.RandomForestClassifier(), - 'metrics': [0, 0, 0, 0] + "lgbm_classifier": {"model": LGBMClassifier(), "metrics": [0, 0, 0, 0]}, + "XGBoost_classifier": { + "model": xg.sklearn.XGBClassifier(), + "metrics": [0, 0, 0, 0], }, - 'gradient_boosting_classifier': { - 'model': ensemble.GradientBoostingClassifier(), - 'metrics': [0, 0, 0, 0] - }, - 'lgbm_classifier': { - 'model': LGBMClassifier(), - 'metrics': [0, 0, 0, 0] - }, - 'XGBoost_classifier': { - 'model': xg.sklearn.XGBClassifier(), - 'metrics': [0, 0, 0, 0] - } } - + return cmodels - + def get_total_models_scores(self, n_clusters=1): + scores = pd.DataFrame(columns=["method", "metric", "mean"]) for model_title, model in self.cmodels.items(): + scores_df = pd.DataFrame(columns=["method", "metric", "mean"]) print("\n************************************\n") print("Current model:", model_title, end="\n") - print("Acc:", model['metrics'][0]/n_clusters) - print("Precision:", model['metrics'][1]/n_clusters) - print("Recall:", model['metrics'][2]/n_clusters) - print("F1:", model['metrics'][3]/n_clusters) \ No newline at end of file + print("Acc:", model["metrics"][0] / n_clusters) + scores_df.append( + { + "method": model_title, + "metric": "test_accuracy", + "mean": model["metrics"][0] / n_clusters, + } + ) + print("Precision:", model["metrics"][1] / n_clusters) + scores_df.append( + { + "method": model_title, + "metric": "test_precision", + "mean": model["metrics"][1] / n_clusters, + } + ) + print("Recall:", model["metrics"][2] / n_clusters) + scores_df.append( + { + "method": model_title, + "metric": "test_recall", + "mean": model["metrics"][2] / n_clusters, + } + ) + print("F1:", model["metrics"][3] / n_clusters) + scores_df.append( + { + "method": model_title, + "metric": "test_f1", + "mean": model["metrics"][3] / n_clusters, + } + ) + scores = pd.concat([scores, scores_df]) + return scores