cls = RandomForestClassifier()
reg = RandomForestRegressor(n_estimators=20, max_features=5, max_depth=None,
min_samples_split=2, min_samples_leaf=1,
max_leaf_nodes=None, bootstrap=True,
oob_score=False, n_jobs=-1)
reg = SVR(C=10., gamma=0.1)
train_df_orig = RevenueCompetition.load_data()
y = train_df_orig['revenue'].values
del train_df_orig['revenue']
test_df_orig = RevenueCompetition.load_data(train=False)
full_df = train_df_orig.append(test_df_orig)
print("Transforming...")
tr = RevenueTransform(rescale=True)
tr.fit(full_df)
X = tr.transform(train_df_orig).values
print('Classify the outliers...')
ly = np.log(y)
ym = ly.mean()
ys = ly.std()
s = np.empty(ly.shape[0])
s[(ly-ym)/ys <= -2] = 0
s[np.logical_and((ly-ym)/ys > -2,(ly-ym)/ys <= -1)] = 1
s[np.logical_and((ly-ym)/ys > -1,(ly-ym)/ys <= 1)] = 2
s[np.logical_and((ly-ym)/ys > 1,(ly-ym)/ys <= 2)] = 3
s[(ly-ym)/ys > 2] = 4
train_index, valid_index = list(StratifiedShuffleSplit(s, n_iter=1, train_size=train_size, random_state=0))[0]
train_size = 0.75
cls = RandomForestClassifier()
reg = RandomForestRegressor(n_estimators=20, max_features=5, max_depth=None,
min_samples_split=2, min_samples_leaf=1,
max_leaf_nodes=None, bootstrap=True,
oob_score=False, n_jobs=-1)
train_df_orig = RevenueCompetition.load_data()
y = train_df_orig['revenue'].values
del train_df_orig['revenue']
test_df_orig = RevenueCompetition.load_data(train=False)
full_df = train_df_orig.append(test_df_orig)
print("Transforming...")
tr = RevenueTransform(rescale=False)
tr.fit(full_df)
X = tr.transform(train_df_orig).values
print('Classify the outliers...')
ly = np.log(y)
ym = ly.mean()
ys = ly.std()
s = np.empty(ly.shape[0])
s[(ly-ym)/ys <= -2] = 0
s[np.logical_and((ly-ym)/ys > -2,(ly-ym)/ys <= -1)] = 1
s[np.logical_and((ly-ym)/ys > -1,(ly-ym)/ys <= 1)] = 2
s[np.logical_and((ly-ym)/ys > 1,(ly-ym)/ys <= 2)] = 3
s[(ly-ym)/ys > 2] = 4
train_index, valid_index = list(StratifiedShuffleSplit(s, n_iter=1, train_size=train_size, random_state=0))[0]
