164 lines
5.0 KiB
Python
164 lines
5.0 KiB
Python
# %%
|
|
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
|
|
import yaml
|
|
from pyprojroot import here
|
|
from sklearn import linear_model, svm, kernel_ridge, gaussian_process, ensemble
|
|
from sklearn.model_selection import LeaveOneGroupOut, cross_val_score, cross_validate, cross_val_predict
|
|
from sklearn.metrics import mean_squared_error, r2_score
|
|
from sklearn.impute import SimpleImputer
|
|
from sklearn.dummy import DummyRegressor
|
|
from sklearn.decomposition import PCA
|
|
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.helper
|
|
|
|
# %%
|
|
segment = "intradaily_30_min"
|
|
target = "JCQ_job_demand"
|
|
csv_name = "./data/" + segment + "_all_targets/input_" + target + "_mean.csv"
|
|
#csv_name = "./data/daily_18_hours_all_targets/input_JCQ_job_demand_mean.csv"
|
|
|
|
# %%
|
|
data_x, data_y, data_groups = machine_learning.helper.prepare_model_input(csv_name)
|
|
|
|
# %%
|
|
data_y.head()
|
|
|
|
# %%
|
|
scores = machine_learning.helper.run_all_models(csv_name)
|
|
|
|
|
|
# %% jupyter={"source_hidden": true}
|
|
logo = LeaveOneGroupOut()
|
|
logo.get_n_splits(
|
|
data_x,
|
|
data_y,
|
|
groups=data_groups,
|
|
)
|
|
|
|
# %% [markdown]
|
|
# ### Baseline: Dummy Regression (mean)
|
|
dummy_regr = DummyRegressor(strategy="mean")
|
|
|
|
# %% jupyter={"source_hidden": true}
|
|
lin_reg_scores = cross_validate(
|
|
dummy_regr,
|
|
X=data_x,
|
|
y=data_y,
|
|
groups=data_groups,
|
|
cv=logo,
|
|
n_jobs=-1,
|
|
scoring=('r2', 'neg_mean_squared_error', 'neg_mean_absolute_error', 'neg_root_mean_squared_error')
|
|
)
|
|
print("Negative Mean Squared Error", np.median(lin_reg_scores['test_neg_mean_squared_error']))
|
|
print("Negative Mean Absolute Error", np.median(lin_reg_scores['test_neg_mean_absolute_error']))
|
|
print("Negative Root Mean Squared Error", np.median(lin_reg_scores['test_neg_root_mean_squared_error']))
|
|
print("R2", np.median(lin_reg_scores['test_r2']))
|
|
|
|
##################
|
|
# %%
|
|
chosen_model = "Random Forest"
|
|
rfr = ensemble.RandomForestRegressor(max_features=0.3, n_jobs=-1)
|
|
rfr_score = cross_validate(
|
|
rfr,
|
|
X=data_x,
|
|
y=data_y,
|
|
groups=data_groups,
|
|
cv=logo,
|
|
n_jobs=-1,
|
|
scoring=('r2', 'neg_mean_squared_error', 'neg_mean_absolute_error', 'neg_root_mean_squared_error')
|
|
)
|
|
print("Negative Mean Squared Error", np.median(rfr_score['test_neg_mean_squared_error']))
|
|
print("Negative Mean Absolute Error", np.median(rfr_score['test_neg_mean_absolute_error']))
|
|
print("Negative Root Mean Squared Error", np.median(rfr_score['test_neg_root_mean_squared_error']))
|
|
print("R2", np.median(rfr_score['test_r2']))
|
|
|
|
# %%
|
|
y_predicted = cross_val_predict(rfr, data_x, data_y, groups=data_groups, cv=logo)
|
|
#########################
|
|
# %%
|
|
chosen_model = "Bayesian Ridge"
|
|
bayesian_ridge_reg = linear_model.BayesianRidge()
|
|
bayesian_ridge_reg_score = cross_validate(
|
|
bayesian_ridge_reg,
|
|
X=data_x,
|
|
y=data_y,
|
|
groups=data_groups,
|
|
cv=logo,
|
|
n_jobs=-1,
|
|
scoring=('r2', 'neg_mean_squared_error', 'neg_mean_absolute_error', 'neg_root_mean_squared_error')
|
|
)
|
|
print("Negative Mean Absolute Error", np.median(bayesian_ridge_reg_score['test_neg_mean_absolute_error']))
|
|
print("Negative Root Mean Squared Error", np.median(bayesian_ridge_reg_score['test_neg_root_mean_squared_error']))
|
|
print("R2", np.median(bayesian_ridge_reg_score['test_r2']))
|
|
|
|
# %%
|
|
y_predicted = cross_val_predict(bayesian_ridge_reg, data_x, data_y, groups=data_groups, cv=logo)
|
|
|
|
# %%
|
|
data_y = pd.DataFrame(pd.concat([data_y, data_groups], axis=1))
|
|
data_y.rename(columns={"target": "y_true"}, inplace=True)
|
|
data_y["y_predicted"] = y_predicted
|
|
|
|
# %%
|
|
data_y.head()
|
|
|
|
# %%
|
|
g1 = sns.relplot(data=data_y, x="y_true", y="y_predicted")
|
|
#g1.set_axis_labels("true", "predicted")
|
|
#g1.map(plt.axhline, y=0, color=".7", dashes=(2, 1), zorder=0)
|
|
#g1.map(plt.axline, xy1=(0,0), slope=1)
|
|
g1.set(title=",".join([segment, target, chosen_model]))
|
|
display(g1)
|
|
g1.savefig("_".join([segment, target, chosen_model, "_relplot.pdf"]))
|
|
|
|
# %%
|
|
data_y_long = pd.wide_to_long(
|
|
data_y.reset_index(),
|
|
i=["local_segment", "pid"],
|
|
j="value",
|
|
stubnames="y",
|
|
sep="_",
|
|
suffix=".+",
|
|
)
|
|
|
|
# %%
|
|
data_y_long.head()
|
|
# %%
|
|
g2 = sns.displot(data_y_long, x="y", hue="value", binwidth=0.1, height=5, aspect=1.5)
|
|
sns.move_legend(g2, "upper left", bbox_to_anchor=(.55, .45))
|
|
g2.set(title=",".join([segment, target, chosen_model]))
|
|
g2.savefig("_".join([segment, target, chosen_model, "hist.pdf"]))
|
|
|
|
# %%
|
|
pca = PCA(n_components=2)
|
|
pca.fit(data_x)
|
|
print(pca.explained_variance_ratio_)
|
|
|
|
# %%
|
|
data_x_pca = pca.fit_transform(data_x)
|
|
data_pca = pd.DataFrame(pd.concat([data_y.reset_index()["y_true"], pd.DataFrame(data_x_pca, columns = {"pca_0", "pca_1"})], axis=1))
|
|
|
|
# %%
|
|
data_pca
|
|
# %%
|
|
|
|
g3 = sns.relplot(data = data_pca, x = "pca_0", y = "pca_1", hue = "y_true", palette = sns.color_palette("Spectral", as_cmap=True))
|
|
g3.set(title=",".join([segment, target, chosen_model]) + "\n variance explained = " + str(round(sum(pca.explained_variance_ratio_), 2)))
|
|
g3.savefig("_".join([segment, target, chosen_model, "_PCA.pdf"]))
|
|
|
|
# %%
|