def predictFluSeq(seqs): # Seqs is the file path of your FASTA files
#returns cross-val scores and MSE
X0 = []
# adding to X and y
for i in range(0, len(seqs) - 1):
X0.append(seqs[i].seq)
y0 = []
for j in range(1, len(seqs)):
y0.append(seqs[i].seq)
from Encoding_v2 import encoding
# Encoding letters into numbers
X = []
for k in range(len(X0)):
encoded_X = encoding(X0[k])
X.append(encoded_X)
y = []
for l in range(len(y0)):
encoded_y = encoding(y0[l])
y.append(encoded_y)
from sklearn.model_selection import cross_val_score, train_test_split
from sklearn import ensemble, metrics
# Cross-Validation
rfr = ensemble.RandomForestRegressor()
rfrscores = cross_val_score(rfr, X, y, cv=2)
cv_score = ("Random Forests cross-validation score", rfrscores)
avg_cv_score = ("Average Cross-Val Accuracy: %0.2f (+/- %0.2f)" %
(rfrscores.mean() * 100, rfrscores.std() * 100))
# Mean Squared Error
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.5,
random_state=50)
rfr.fit(X_train, y_train)
y_predicted = rfr.predict(X_test)
mse_score = ('Random Forests MSE:',
metrics.mean_squared_error(y_test, y_predicted))
return cv_score, avg_cv_score, mse_score
def predictFluSeq(seqs): # Seqs is the file path of your FASTA files
#returns cross-val scores and MSE
X0 = []
# adding to X and y
for i in range(0, len(seqs) - 1):
X0.append(seqs[i].seq)
y0 = []
for j in range(1, len(seqs)):
y0.append(seqs[i].seq)
from Encoding_v2 import encoding
# Encoding letters into numbers
X = []
for k in range(len(X0)):
encoded_X = encoding(X0[k])
X.append(encoded_X)
y = []
for l in range(len(y0)):
encoded_y = encoding(y0[l])
y.append(encoded_y)
from sklearn import ensemble, cross_validation, metrics
# Cross-Validation
rfr = ensemble.RandomForestRegressor()
rfrscores = cross_validation.cross_val_score(rfr, X, y, cv=2)
cv_score = ("Random Forests cross-validation score", rfrscores)
avg_cv_score = ("Average Cross-Val Accuracy: %0.2f (+/- %0.2f)" % (rfrscores.mean()*100, rfrscores.std() *100))
# Mean Squared Error
X_train,X_test,y_train,y_test = cross_validation.train_test_split(X,y,test_size=0.5,random_state=50)
rfr.fit(X_train,y_train)
y_predicted = rfr.predict(X_test)
mse_score = ('Random Forests MSE:', metrics.mean_squared_error(y_test,y_predicted))
return cv_score, avg_cv_score, mse_score
#adding to X and y
for i in range(0, len(new) - 1):
X0.append(new[i].seq)
#print len(X0)
y0 = []
for j in range(1, len(new)):
y0.append(new[i].seq)
from Encoding_v2 import encoding
X = []
for k in range(len(X0)):
encoded_X = encoding(X0[k])
X.append(encoded_X)
y = []
for l in range(len(y0)):
encoded_y = encoding(y0[l])
y.append(encoded_y)
'''
print len(X[0])
print len(y[298])
a = [1,2,3,4,5]
print len(a)
from Compare_Strains import test_length
#adding to X and y
for i in range(0,len(new)-1):
X0.append(new[i].seq)
y0 = []
for j in range(1,len(new)):
y0.append(new[i].seq)
from Encoding_v2 import encoding
# Changing A,C,T,G into 1,2,3,4
X = []
for k in range(len(X0)):
encoded_X = encoding(X0[k])
X.append(encoded_X)
y = []
for l in range(len(y0)):
encoded_y = encoding(y0[l])
y.append(encoded_y)
# Using sklearn models for prediction
from sklearn import tree
dtr = tree.DecisionTreeRegressor()
dtr.fit(X,y)
from sklearn import cross_validation
dtrscores = cross_validation.cross_val_score(dtr,X,y,cv=2)
#adding to X and y
for i in range(0, len(new) - 1):
X0.append(new[i].seq)
y0 = []
for j in range(1, len(new)):
y0.append(new[i].seq)
from Encoding_v2 import encoding, decoding, compare_sequences
# Encoding
X = []
for k in range(len(X0)):
encoded_X = encoding(X0[k])
X.append(encoded_X)
y = []
for l in range(len(y0)):
encoded_y = encoding(y0[l])
y.append(encoded_y)
# ML and accuracy
from sklearn import tree
dtr = tree.DecisionTreeRegressor()
dtr.fit(X, y)
from sklearn.model_selection import cross_val_score, train_test_split
dtrscores = cross_val_score(dtr, X, y, cv=2)
print('Decision Trees', dtrscores)
