criterion = args.criterion
max_depth = args.max_depth
min_samples_split = args.min_samples_split
result_path = args.result_path
feature_filter = args.feature_filter
data = pd.read_csv(training_set_path, index_col=0)
paths = [
test_path + catalog + '_sampled_' + str(i) + '.csv'
for i in xrange(100)
]
# Necesito asegurarme de que las curvas sean las mismas en train y test
test_data = pd.read_csv(paths[0], index_col=0)
data, test_data = utils.equalize_indexes(data, test_data)
data, y = utils.filter_data(data, feature_filter=feature_filter)
skf = cross_validation.StratifiedKFold(y, n_folds=folds)
results = []
ids = []
for train_index, test_index in skf:
train_X, train_y = data.iloc[train_index], y.iloc[train_index]
clf = None
clf = RandomForestClassifier(n_estimators=n_estimators,
criterion=criterion,
max_depth=max_depth,
# coding=utf-8
# Script solo pa recordar como separe los sets de testing para eros y macho. No esta
# pensado para correrse normalmente
# -----------------------------------------------------------------------------
from sklearn import cross_validation
import pandas as pd
import utils
catalog = 'EROS'
test_size = 5000
normal_df = pd.read_csv('/n/home09/ncastro/workspace/Features/sets/' + catalog + '/' + catalog + '_regular_set_5.csv', index_col=0)
sample_df = pd.read_csv('/n/seasfs03/IACS/TSC/ncastro/sets/' + catalog + '_Sampled/uniform/5%/' + catalog + '_sampled_0.csv', index_col=0)
a, b = utils.equalize_indexes(normal_df, sample_df)
sss = cross_validation.StratifiedShuffleSplit(a['class'], n_iter=1, test_size=test_size,
random_state=1)
for train_index, test_index in sss:
train_df = a.iloc[train_index]
test_df = a.iloc[test_index]
a.to_csv('/n/home09/ncastro/workspace/Features/sets/Common/' + catalog + '.csv')
test_df.to_csv('/n/home09/ncastro/workspace/Features/sets/Common/' + catalog + '_test.csv')
n_estimators = args.n_estimators
criterion = args.criterion
max_depth = args.max_depth
min_samples_split = args.min_samples_split
feature_filter = args.feature_filter
index_filter = args.index_filter
if index_filter is not None:
index_filter = pd.read_csv(index_filter, index_col=0).index
train_data = pd.read_csv(train_path, index_col=0)
test_data = pd.read_csv(test_path, index_col=0)
train_data, test_data = utils.equalize_indexes(train_data, test_data)
train_X, train_y = utils.filter_data(train_data, index_filter=index_filter, feature_filter=feature_filter)
test_X, test_y = utils.filter_data(test_data, index_filter=index_filter, feature_filter=feature_filter)
# Ocupo solo los datos de test para hacer el k-fold, por que estos no estan repetidos
# Y es valido ocuparlos solo por posicion
skf = cross_validation.StratifiedKFold(test_y, n_folds=folds)
results = []
ids = []
for train_index, test_index in skf:
if inverse:
aux = train_index
train_index = test_index
test_index = aux
n_estimators = args.n_estimators
criterion = args.criterion
max_depth = args.max_depth
min_samples_split = args.min_samples_split
feature_filter = args.feature_filter
index_filter = args.index_filter
if index_filter is not None:
index_filter = pd.read_csv(index_filter, index_col=0).index
train_data = pd.read_csv(train_path, index_col=0)
test_data = pd.read_csv(test_path, index_col=0)
train_data, test_data = utils.equalize_indexes(train_data, test_data)
train_X, train_y = utils.filter_data(train_data,
index_filter=index_filter,
feature_filter=feature_filter)
test_X, test_y = utils.filter_data(test_data,
index_filter=index_filter,
feature_filter=feature_filter)
# Ocupo solo los datos de test para hacer el k-fold, por que estos no estan repetidos
# Y es valido ocuparlos solo por posicion
skf = cross_validation.StratifiedKFold(test_y, n_folds=folds)
results = []
ids = []
for train_index, test_index in skf:
n_estimators = args.n_estimators
criterion = args.criterion
max_depth = args.max_depth
min_samples_split = args.min_samples_split
result_path = args.result_path
feature_filter = args.feature_filter
data = pd.read_csv(training_set_path, index_col=0)
paths = [test_path + catalog + '_sampled_' + str(i) + '.csv' for i in xrange(100)]
# Necesito asegurarme de que las curvas sean las mismas en train y test
test_data = pd.read_csv(paths[0], index_col=0)
data, test_data = utils.equalize_indexes(data, test_data)
data, y = utils.filter_data(data, feature_filter=feature_filter)
skf = cross_validation.StratifiedKFold(y, n_folds=folds)
results = []
ids = []
for train_index, test_index in skf:
train_X, train_y = data.iloc[train_index], y.iloc[train_index]
clf = None
clf = RandomForestClassifier(n_estimators=n_estimators, criterion=criterion,
max_depth=max_depth, min_samples_split=min_samples_split,
n_jobs=n_processes)
