def cascade():
"""
:return:
Beginning of cascade classification. Still being developed.
"""
pred = 0
bdt = joblib.load('models/adaboost256.pkl')
frame = cv2.imread('images/gradient.jpg')
# X = cf.compute_chans(frame).ravel().reshape(1, -1)
# X = cf.compute_chans(cv2.resize(frame, (64, 128))).ravel().reshape(1, -1)
x = cf.compute_chans(cv2.resize(frame, (64, 128))).ravel()
# np.random.shuffle(x)
N = 100
pred = [None] * N
X = np.array([x for i in range(N)])
start = time.time()
for i in range(N):
for t, estimator in enumerate(bdt.estimators_):
pred += _samme_proba(estimator, 2, X)
p_t = pred[0, 1] / (t + 1)
print('p_t is: ', p_t)
if p_t < -.2 and t > 8:
return False
return False
out = casc.cascade(X, bdt)
print((time.time() - start) / N)
start = time.time()
for i in range(N):
out = bdt.predict(X)
print((time.time() - start) / N)
print(type(bdt))
def get_aggressive_tweets(tweets):
content = [t[1] for t in tweets]
id_date = [(t[0], t[2]) for t in tweets]
results = []
write_out_data(
tweets, '/proj/nlp/users/terra/streaming_results/correlate_tmp.csv')
predictions = cascade(
'/proj/nlp/users/terra/streaming_results/correlate_tmp.csv')
for p in range(0, len(predictions)):
if predictions[p] == 1:
results.append(id_date[p])
return results
# -*- coding: utf-8 -*-
"""
Created on Thu Oct 16 21:49:56 2014
@author: haggertr
"""
from matrix_from_xls import matrix_from_xls as mfx
import sys
sys.path.append('c:\\code\\cascade\\') # location of module
import cascade as csc
#file = 'C:\\Users\\haggertr\\Desktop\\Documents\\work - OSU\\research\\WW2100\\Research\\results2\\Cascade_plots\\save tmp\\testdata.xls'
#file = 'C:\\code\\matrix-from-data\\testdata.xls'
file = 'C:\\code\\matrix-from-data\\WS1_CO2.xls'
#file = '1e__IjqMLBBVLqBHWZiIORkPbz6W8PQlSPVeodQBM8Oc' #google key. Add kwarg filetype='gsheet'
a = mfx(file,1,48,16)
b = csc.cascade(a)
print b
def train(self, labeledPoints):
labeledPoints = cascade(labeledPoints, self._reduce, self.nmax)
X, y = self._readiterator(labeledPoints)
self.model = self.create_model()
self.model.fit(X, y)
def train(self, labeledPoints):
labeledPoints = cascade(labeledPoints, self._reduce, self.nmax)
X, y = self._readiterator(labeledPoints)
self.model = self.create_model()
self.model.fit(X, y)
def cascadeCallback(self, sender):
cascade()
G = nx.from_pandas_edgelist(df, 'from', 'to', create_using=nx.DiGraph()) #%% Launch Cascade Model from cascade import cascade import random df = dfRaw[94000:94100] # Assign Random Seed Vertices n = 2 seeds = random.sample(list(set(df['from'])), n) #seeds = init_seeds; # Run Cascade Model df, df_inf, steps = cascade(seeds, df) #%% # Rename 'edgelist' to dataframe #df = edgelist; # Handle edgelist unweighted networks with uniform weights # Assign likelihood of adoption for all vertices df['willingness'] = df['willingness'].apply(lambda x: random.random()) df['influenced'] = np.zeros((len(df), 1)) # Assign "influenced" values of 10 to seeded nodes df['influenced'] = np.where(df['from'].isin(seeds), 10, 0) steps = 0
def train(self, labeledPoints):
labeledPoints = cascade(labeledPoints, self._reduce, self.nmax)
self.X, y = self._readiterator(labeledPoints)
# final model does not need regularization
self.model, self.support = self._fit(self.X, y, newC=self.C * 10.0)
def cascadeCallback(self, sender):
cascade()
for k in [5]:
for method in ['greedy', 'random', 'out-degree', 'closeness centrality']:
print(str(k))
start = time.time()
if method == 'greedy':
A = greedy(k, p, 50, G, nodes, edges)
if method == 'random':
A = set(random.sample(nodes, k))
if method == 'closeness centrality':
A = centrality(G, k)
if method == 'out-degree':
A = out_degree(G, k)
end = time.time()
#test results#
nodes_reached, GX = cascade(G, A, p)
out_file.write('%s\t%s\t%f\t%d\t%d\n' %
(method, str(A), end - start, k, nodes_reached))
out_file.flush()
out_file.close()
def on_evolving_train_config_activate(self, radiobutton, data=None):
"""For showing window for configuring parameters related to cascade
Training."""
wcascade = cascade()
def train(self, labeledPoints):
labeledPoints = cascade(labeledPoints, self._reduce, self.nmax)
self.X, y = self._readiterator(labeledPoints)
# final model does not need regularization
self.model, self.support = self._fit(self.X, y, newC=self.C * 10.0)
def on_evolving_train_config_activate(self,radiobutton,data=None):
"""For showing window for configuring parameters related to cascade
Training."""
wcascade=cascade()
