manager.assign_sets(train=train)
tup = manager.create_mask(
train.iloc[:, :-1],
global_dirs.variable_selection[0],
select=global_dirs.variable_selection[1]
) # This tuple shouldn't take care about y_column index
scalers = manager.preprocess_train(tup, scale_Y=False)
dnn_model = manager.fit_dnn_regression([(9, 'relu'), (18, 'relu'),
(56, 'relu'), (11, 'relu'),
(10, 'relu')],
epochs=300,
batch_size=30,
use_dropout=False)
results = manager.predict_dnn_regression(test, tup)
#X_train = train.loc[:, train.columns != train.columns[-1]]
#X_test = test.loc[:, test.columns != test.columns[-1]]
#var_selection = reader.create_mask(X_train, global_dirs.variable_selection[0], select=global_dirs.variable_selection[1])
#X_train = X_train.loc[:, var_selection]
#X_test = X_test.loc[:, var_selection]
#y_train = train.loc[:, train.columns[-1]]
#y_test = test.loc[:, test.columns[-1]]
#X_train = scaler_X.fit_transform(X_train)
#X_test = scaler_X.transform(X_test)
"oxygen": "green",
"iron": "orange",
}
dec_round = 3
plt.rc('axes', labelsize=25)
plt.rc('axes', titlesize=25)
plt.rc('legend', fontsize=15)
plt.rc('xtick', labelsize=15)
plt.rc('ytick', labelsize=15)
results = None
for name, ds in test.items():
results = manager.predict_dnn_regression(ds, tup)
f, ax = plt.subplots(1, 2)
# Histogram of differences
ax[0].hist(results["differences"],
color=colors[name],
histtype="step",
lw=2)
ax[0].axvline(x=0)
ax[0].set_title(
"Deep Neural Net\nQGSJET-II (test)\nHistogram of differences - {}".
format(name))
ax[0].set_xlabel(r'$S_{\mu}^{real} - S_{\mu}^{pred}$')
ax[0].set_ylabel("Count")
dmean_patch = mpatches.Patch(color='white',
label='Diff. mean: {}'.format(
