from seq_reader import load_data
from ohv import get_rep_mats, conv_labels
import numpy as np
from sklearn.model_selection import StratifiedKFold
from keras.datasets import mnist
from keras.layers import Dense, Dropout, Activation, Flatten, Convolution2D, MaxPooling2D
from keras.models import Sequential
from keras.utils import np_utils
seed = 123
np.random.seed(seed)
X, y = load_data("dataset/data.txt")
X = get_rep_mats(X)
for i in X:
for idx, j in enumerate(i):
i[idx] = j[0]
y = conv_labels(y)
X = np.asarray(X)
Y = np.asarray(y)
kfs = StratifiedKFold(n_splits=10, shuffle=True, random_state=seed)
scores = []
for train, test in kfs.split(X, Y):
print("----> FOLD [" + str(len(scores) + 1) + "]")
Xtr = X[train].reshape(X[train].shape[0], 1, 58, 64)
Xts = X[test].reshape(X[test].shape[0], 1, 58, 64)
Xtr = Xtr.astype('float32')
Xts = Xts.astype('float32')
np.random.seed(123) # for reproducibility
# In[5]:
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D
from keras.utils import np_utils
from keras.datasets import mnist
#############################################
# In[6]:
# 1. Load data into train and test sets
X, y = load_data("../data/promoters.data.txt") # sequences, labels
X = get_rep_mats(X) # convert to array of representation matrices
############
# In[ ]:
for i in X:
for idx, j in enumerate(i):
i[idx] = j[0]
############
# In[ ]:
y = conv_labels(y, "promoter") # convert to integer labels
X = np.asarray(X) # work with np arrays
y = np.asarray(y)
from sklearn.model_selection import StratifiedKFold # cross validation
import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D
from keras.utils import np_utils
from keras.datasets import mnist
#############################################
seed = 123 # for reproducibility
np.random.seed(seed)
# 1. Load data into train and test sets
X, y = load_data("../data/splice.data.txt") # sequences, labels
X = get_rep_mats(X) # convert to array of representation matrices
for i in X: # CUSTOM reshape
for idx, j in enumerate(i):
i[idx] = j[0]
y = conv_labels(y) # convert to integer labels
X = np.asarray(X) # work with np arrays
Y = np.asarray(y)
# define 10-fold cross validation test harness
kfold = StratifiedKFold(n_splits=10, shuffle=True, random_state=seed)
scores = []
for train, test in kfold.split(X, Y):
print "====> FOLD [" + str(len(scores) + 1) + "]"