def get_rand_docs(db, patient, state, num=500):
collection = db[patient]
df = shelve_api.load('labeled_' + patient)
selection = df[df['state'] == state]
l_id = list(selection['_id'])
random.shuffle(l_id)
l_id = l_id[:num]
l_id = [ObjectId(post_id) for post_id in l_id]
query = {'state': state, '_id': {'$in': l_id}}
return collection.find(query)
def load_shelve(name):
return shelve_api.load(name)
def load_shelve(name):
return shelve_api.load(name)
from sklearn.linear_model import LinearRegression
from sklearn.cross_validation import StratifiedKFold
import numpy as np
from sklearn.metrics import classification_report
from sklearn.metrics import roc_auc_score
from tests import shelve_api
XX, yy = shelve_api.load('lr')
X = XX[2700:]
y = yy[2700:]
clf = LinearRegression(normalize=True)
skf = StratifiedKFold(y, n_folds=2)
for train_index, test_index in skf:
print("Detailed classification report:")
print()
print("The model is trained on the full development set.")
print("The scores are computed on the full evaluation set.")
print()
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
# clf.fit(X_train, y_train)
y_true, y_pred = y_test, clf.predict(X_test)
for i, num in enumerate(y_pred):
if num < 0.0:
y_pred[i] = 0.0
continue
elif num > 1.0:
self.X = []
self.y = []
def verbose_svm(self):
skf = StratifiedKFold(self.y, n_folds=2)
print(self.name)
for train_index, test_index in skf:
print("Detailed classification report:")
print()
print("The model is trained on the full development set.")
print("The scores are computed on the full evaluation set.")
print()
X_train, X_test = self.X[train_index], self.X[test_index]
PCA = self.get_pca()
PCA.fit(self.X)
y_train, y_test = self.y[train_index], self.y[test_index]
SVC = self.get_svm()
X_train = PCA.transform(X_train)
SVC.fit(X_train, y_train)
X_test = PCA.transform(X_test)
y_true, y_pred = y_test, SVC.predict(X_test)
print(classification_report(y_true, y_pred))
print()
print(roc_auc_score(y_true, y_pred))
print()
if __name__ == "__main__":
clf = RawClf('Dog_1',
data=(shelve_api.load('clf_x'), shelve_api.load('clf_y')))
self.y = []
def verbose_svm(self):
skf = StratifiedKFold(self.y, n_folds=2)
print(self.name)
for train_index, test_index in skf:
print("Detailed classification report:")
print()
print("The model is trained on the full development set.")
print("The scores are computed on the full evaluation set.")
print()
X_train, X_test = self.X[train_index], self.X[test_index]
PCA = self.get_pca()
PCA.fit(self.X)
y_train, y_test = self.y[train_index], self.y[test_index]
SVC = self.get_svm()
X_train = PCA.transform(X_train)
SVC.fit(X_train, y_train)
X_test = PCA.transform(X_test)
y_true, y_pred = y_test, SVC.predict(X_test)
print(classification_report(y_true, y_pred))
print()
print(roc_auc_score(y_true, y_pred))
print()
if __name__ == "__main__":
clf = RawClf('Dog_1', data=(shelve_api.load('clf_x'), shelve_api.load('clf_y')))
def get_min_max(patient):
mm = sapi.load("%s_mm" % patient)
return (np.min(mm), np.max(mm))
from sklearn.cross_validation import StratifiedKFold
import numpy as np
from sklearn.metrics import classification_report
from sklearn.metrics import roc_auc_score
from sklearn.neighbors import KNeighborsClassifier
from tests import shelve_api
def yield_patient_names(name, d):
for key in d:
if name in key:
yield key
new_d = {}
d = shelve_api.load('baseline')
for key in yield_patient_names('Dog_1', d):
new_d[key] = d[key]
for key in yield_patient_names('Dog_2', d):
new_d[key] = d[key]
for key in yield_patient_names('Dog_3', d):
new_d[key] = d[key]
for key in yield_patient_names('Dog_4', d):
new_d[key] = d[key]
# for key in yield_patient_names('Dog_5', d):
# new_d[key] = d[key]
# store = pd.HDFStore("D:/gingivere/data.h5")
# data = store['baseline']
# store.close()
def get_min_max(patient):
mm = sapi.load("%s_mm" % patient)
return (np.min(mm), np.max(mm))
