p_dict = {}
r_dict = {}
f_dict = {}
w_dict = {}
files = [f for f in os.listdir(result_dir) if '.csv' in f]
for f in files:
pattern = re.compile('[0-9]+')
percentage = int(pattern.search(f).group())
result = pd.read_csv(result_dir + 'result_' + str(percentage) + '.csv', index_col=0)
if how == 'soft':
matrix = metrics.confusion_matrix(result)
elif how == 'hard':
matrix = metrics.hard_matrix(result)
matrix.to_csv(path + 'Metricas/' + how + '_matrix_' + str(percentage) + '.csv')
w_dict[percentage] = metrics.weighted_f_score(matrix)
clases = matrix.columns.tolist()
p = [metrics.precision(matrix, c) for c in clases]
r = [metrics.recall(matrix, c) for c in clases]
f = [metrics.f_score(matrix, c) for c in clases]
p_dict[percentage] = p
r_dict[percentage] = r
f_dict[percentage] = f
save_dir = path + 'Metricas/'
]
paths = paths[0:10]
# Entreno y clasifico con árboles
partial_fit = partial(parallel.fit_tree,
feature_filter=feature_filter,
folds=folds)
pool = Pool(processes=n_processes, maxtasksperchild=2)
resultados_tree = pool.map(partial_fit, paths)
pool.close()
pool.join()
# Imprimo y guardo resultados obtenidos
for i, r in enumerate(resultados_tree):
r.to_csv(result_path + 'result_tree_' + str(i) + '.csv')
matrix = metrics.hard_matrix(r)
print 'Tree ' + str(i) + ' f_score: ' + str(
metrics.weighted_f_score(matrix))
# Entreno y clasifico con rf
partial_fit = partial(parallel.fit_rf,
feature_filter=feature_filter,
folds=folds)
pool = Pool(processes=n_processes, maxtasksperchild=2)
resultados_rf = pool.map(partial_fit, paths)
pool.close()
pool.join()
# Imprimo y guardo resultados obtenidos
for i, r in enumerate(resultados_rf):
r.to_csv(result_path + 'result_rf_' + str(i) + '.csv')
feature_filter = args.feature_filter
paths = [sets_path + catalog + '_sampled_' + str(i) + '.csv' for i in xrange(100)]
paths = paths[0:10]
# Entreno y clasifico con árboles
partial_fit = partial(parallel.fit_tree, feature_filter=feature_filter, folds=folds)
pool = Pool(processes=n_processes, maxtasksperchild=2)
resultados_tree = pool.map(partial_fit, paths)
pool.close()
pool.join()
# Imprimo y guardo resultados obtenidos
for i, r in enumerate(resultados_tree):
r.to_csv(result_path + 'result_tree_' + str(i) + '.csv')
matrix = metrics.hard_matrix(r)
print 'Tree ' + str(i) + ' f_score: ' + str(metrics.weighted_f_score(matrix))
# Entreno y clasifico con rf
partial_fit = partial(parallel.fit_rf, feature_filter=feature_filter, folds=folds)
pool = Pool(processes=n_processes, maxtasksperchild=2)
resultados_rf = pool.map(partial_fit, paths)
pool.close()
pool.join()
# Imprimo y guardo resultados obtenidos
for i, r in enumerate(resultados_rf):
r.to_csv(result_path + 'result_rf_' + str(i) + '.csv')
matrix = metrics.hard_matrix(r)
print 'RF ' + str(i) + ' f_score: ' + str(metrics.weighted_f_score(matrix))
valores_accuracy = []
valores_recall = []
valores_fscore = []
x_values = []
x_values_fscore = []
# Para cada porcentaje de confianza
for i in xrange(100):
# Obtengo las predicciones con una confianza mayor a cierto umbral
porcentaje = float(i) / 100
aux = result[result['trust'] > porcentaje]
# matrix = metrics.confusion_matrix(aux)
matrix = metrics.hard_matrix(aux)
# Si la precision es menor que cero, es porque no habian datos que superaran tal nivel de confianza
precision = metrics.accuracy(matrix, clase)
if precision >= 0:
valores_accuracy.append(precision)
valores_recall.append(metrics.recall(matrix, clase))
x_values.append(porcentaje)
# Si el f_score es menor que cero, es porque no habian datos que superaran tal nivel de confianza
f_score = metrics.f_score(matrix, clase)
if f_score >= 0:
valores_fscore.append(f_score)
x_values_fscore.append(porcentaje)
#graf(clase, x_values, valores_accuracy, 'Accuracy')
p_dict = {}
r_dict = {}
f_dict = {}
w_dict = {}
files = [f for f in os.listdir(result_dir) if '.csv' in f]
for f in files:
pattern = re.compile('[0-9]+')
percentage = int(pattern.search(f).group())
result = pd.read_csv(result_dir + 'result_' + str(percentage) + '.csv',
index_col=0)
if how == 'soft':
matrix = metrics.confusion_matrix(result)
elif how == 'hard':
matrix = metrics.hard_matrix(result)
matrix.to_csv(path + 'Metricas/' + how + '_matrix_' + str(percentage) +
'.csv')
w_dict[percentage] = metrics.weighted_f_score(matrix)
clases = matrix.columns.tolist()
p = [metrics.precision(matrix, c) for c in clases]
r = [metrics.recall(matrix, c) for c in clases]
f = [metrics.f_score(matrix, c) for c in clases]
p_dict[percentage] = p
r_dict[percentage] = r
f_dict[percentage] = f
valores_accuracy = [] valores_recall = [] valores_fscore = [] x_values = [] x_values_fscore = [] # Para cada porcentaje de confianza for i in xrange(100): # Obtengo las predicciones con una confianza mayor a cierto umbral porcentaje = float(i)/100 aux = result[result['trust'] > porcentaje] # matrix = metrics.confusion_matrix(aux) matrix = metrics.hard_matrix(aux) # Si la precision es menor que cero, es porque no habian datos que superaran tal nivel de confianza precision = metrics.accuracy(matrix, clase) if precision >= 0: valores_accuracy.append(precision) valores_recall.append(metrics.recall(matrix, clase)) x_values.append(porcentaje) # Si el f_score es menor que cero, es porque no habian datos que superaran tal nivel de confianza f_score = metrics.f_score(matrix, clase) if f_score >= 0: valores_fscore.append(f_score) x_values_fscore.append(porcentaje) #graf(clase, x_values, valores_accuracy, 'Accuracy')
