import learner_functions as lf
import load_data as ld
import feature_selection as fs
import hard_vote as hv
import soft_vote as sv
data = ld.LoadData()
#create test and train labels
gender_labels = data.clinical['gender'].tolist()
MSI_labels = data.clinical['msi'].tolist()
test_gender_labels = data.test_clinical['gender'].tolist()
test_MSI_labels = data.test_clinical['msi'].tolist()
#feature selections and subsetted data
protein_sub_set = fs.univariate(data.proteomic, gender_labels)
selected_protein_columns = list(protein_sub_set.columns.values)
test_protein_sub_set = data.test_proteomic.ix[:, selected_protein_columns]
print('knn')
knn_params = { # Found by parameter optimization in knn-optimization.py
"n_neighbors": 11
}
#train learners for gender and msi here:
knn_gender, knn_gender_score = lf.train_knn(protein_sub_set, gender_labels,
**knn_params)
knn_msi, knn_msi_score = lf.train_knn(protein_sub_set, MSI_labels,
**knn_params)
print('lr')
lr_gender, lr_gender_score = lf.train_lr(protein_sub_set, gender_labels)
]
`y` is mismatch labels:
if x[0][i] matches x[1][i], y[i] == 1.0, else 0.0
"""
self.model.fit(x, [y], **kwargs)
def predict(self, x):
"""`x` is the same as in the `fit()` method.
Returns a list `y` of probabilities of x[0][i] matching x[1][i]
"""
return self.model.predict(x)
if __name__ == "__main__":
data = LoadData()
pro_data = feature_selection.univariate(data.proteomic, data.clinical)
rna_data = feature_selection.univariate(data.rna, data.clinical)
prot_x = pd.concat([pro_data, pro_data])
shuffled_rna = rna_data.sample(frac=1)
rna_x = pd.concat([rna_data, shuffled_rna])
labels = [1.0] * 80 + [0.0] * 80
network = SiameseNet([(pro_data.shape[-1], ), (rna_data.shape[-1], )])
network.fit([prot_x, rna_x], labels, epochs=500, batch_size=5)
truth = pd.read_csv("./data/tidy/sum_tab_2.csv")
truth['Score'] = network.predict([pro_data, rna_data])
truth.to_csv("./data/tidy/output/siamese_scores.csv", index=False)
import learner_functions as lf
import load_data as ld
import feature_selection as fs
import find_mismatch as fm
import pandas as pd
data = ld.LoadData()
#create test and train labels
gender_labels = data.clinical['gender'].tolist()
MSI_labels = data.clinical['msi'].tolist()
test_gender_labels = data.test_clinical['gender'].tolist()
test_MSI_labels = data.test_clinical['msi'].tolist()
mismatch_labels = data.mismatch['mismatch'].tolist()
protein_sub_set = fs.univariate(data.proteomic, mismatch_labels)
rna_sub_set = fs.univariate(data.rna, mismatch_labels)
knn_params = { # Found by parameter optimization in knn-optimization.py
"n_neighbors": 11
}
# train models for predicting mislabels based on all 3 data sets
lf.train_rf(data.train_all.fillna(0), data.mislabel_labels)
# ************************************
# TESTING TO FIND MISMATCH INDICES
# knn_rna, knn_rna_score = lf.train_knn(rna_sub_set, mismatch_labels, **knn_params)
# knn_protein, knn_protein_score = lf.train_knn(protein_sub_set, mismatch_labels, **knn_params)
#
# lr_rna, lr_rna_score = lf.train_lr(rna_sub_set,mismatch_labels)
def select_features(self):
self.rna = univariate(self.rna, self.clinical)
self.proteomic = univariate(self.proteomic, self.clinical)
self.test_rna = self.test_rna[self.rna.columns]
self.test_proteomic = self.test_proteomic[self.proteomic.columns]