import progressbar
import numpy as np
from sklearn.metrics import matthews_corrcoef
import time, os
from utils import load_training_subset_1110, read_variable
#%
val_X, val_Y = load_training_subset_1110(range(1000, 1184, 1))
#%%
print('loading trees...')
model_forest = []
bar = progressbar.ProgressBar()
for set_id in bar(range(0, 300, 1)):
model = read_variable('9/forest_' + str(set_id) + '.pkl')
model_forest.append(model)
#%%
#%%
print('loading logic...')
model_logic = []
bar = progressbar.ProgressBar()
for set_id in bar(range(0, 166, 1)):
model = read_variable('7/logic_' + str(set_id) + '.pkl')
model_logic.append(model)
#%%
print('loading boost...')
model_boost = []
bar = progressbar.ProgressBar()
for set_id in bar(range(0, 166, 1)):
model = read_variable('7/boost_' + str(set_id) + '.pkl')
import time
from utils import load_training_subset_1110, read_variable, save_variable
import numpy as np
from sklearn.metrics import matthews_corrcoef
#%%
val_X, val_Y = load_training_subset_1110(range(1000, 1010, 1))
tr_X_1s = read_variable('model_stats/tr_pip_data_1s_1110.pkl')
#%%
'''
Model: SGD
'''
from sklearn.linear_model import SGDClassifier
len_1s = tr_X_1s.shape[0]
for set_id in range(0, 166, 1):
chunk_range = range(set_id, 1000, 166)
t_X, t_Y = load_training_subset_1110(chunk_range)
tr_X = np.concatenate([t_X, tr_X_1s])
tr_Y = np.concatenate([t_Y, np.ones(len_1s)])
alpha = 1e-4 # default
#‘none’, ‘l2’, ‘l1’, or ‘elasticnet’
penalty = 'l1'
model = SGDClassifier(alpha=alpha, shuffle=True, n_jobs=3, penalty=penalty)
t0 = time.time()
model = model.fit(tr_X, tr_Y)
import progressbar
import numpy as np
from sklearn.metrics import matthews_corrcoef
import time, os
from utils import load_training_subset_1110,read_variable, save_variable
#%
val0_X,val0_Y = load_training_subset_1110(range(0,100,1))
val1_X,val1_Y = load_training_subset_1110(range(1000,1100,1))
#%
print('loading trees...')
model_forest = []
bar = progressbar.ProgressBar()
for set_id in bar(range(0,300,1)):
model = read_variable('9/forest_'+str(set_id)+'.pkl')
model_forest.append(model)
forest_2nd = read_variable('forest_2nd.pkl')
#%%
models_single_type = model_forest
X,Y = val0_X,val0_Y
votes0 = np.zeros([X.shape[0],len(models_single_type)])
model_mccs = np.zeros(len(models_single_type))
for model_id,model in enumerate(models_single_type):
t0 = time.time()
pred_Y = model.predict_proba(X)
pred_Y_0 = pred_Y[:,0]
votes0[:,model_id] = pred_Y_0