def conditional_random_fields(X, y):
"""
"""
X_ = [(np.atleast_2d(x), np.empty((0, 2), dtype=np.int)) for x in X]
Y = y.reshape(-1, 1)
X_train, X_test, y_train, y_test = train_test_split(X_, Y)
pbl = GraphCRF()
svm = OneSlackSSVM(pbl)
svm.fit(X_train, y_train)
y_pred = np.vstack(svm.predict(X_test))
print("Score with pystruct crf svm: %f "
% (np.mean(y_pred == y_test)))
print classification_report(y_test, y_pred)
plot_confusion_matrix(y_test, y_pred)
def main(filenames, filename_pheno, phenos):
"""
"""
ids, X = [], []
snps = None
for file in filenames:
ids_t, X_t, snps = load_npz(file)
ids.append(ids_t)
X.append(X_t)
ids = np.concatenate(ids, axis=0)
X = np.concatenate(X, axis=0)
data_pheno_ear = RawDataPheno(filename_pheno, phenos)
df_pheno_ear = data_pheno_ear.get_pheno()
merged_df = merge_geno_pheno(df_pheno_ear, ids, X, snps)
norm_x = normalization(merged_df.ix[:,2:])
X_pca = get_PCA(norm_x)
#merged_df[data_pheno.pheno_name[1]].replace(to_replace=-1, value=0, inplace=True)
merged_df[data_pheno_ear.pheno_name[-1]] = merged_df[data_pheno_ear.pheno_name[-1]].astype(np.int)
y = merged_df[data_pheno_ear.pheno_name[-1]].values
print "Pheno working : {}".format(data_pheno_ear.pheno_name[-1])
"""if np.nan in y or -1 in y:
print "hay nan :("
else:
print "la muestra esta completa"
"""
plot_PCA(X_pca, y)
#conditional_random_fields(norm_x, y)
X_train, X_test, y_train, y_test = train_test_split(norm_x, y)
clf = support_vector(X_train, y_train)
clf = extra_tree(X_train, y_train)
y_pred = clf.predict(X_test)
clf.score(X_test, y_test)
print classification_report(y_test, y_pred)
plot_confusion_matrix(y_test, y_pred)
