def preprocess_alt(df, to_clf, red_corr=True, tr=0.90, n=3, normalization=None ,ignore_classes=[],
mean_by=None,remove_outliers=None, train_ratio=0.7, as_df =False,random_state=42):
data = df.copy()
if mean_by != None:
data = mean_df(data, mean_by)
if normalization != None:
data = normalize(data, ignore_classes,to_clf, norm=normalization)
if red_corr:
data = red_correlations(data, to_clf,tr=tr, n=n)
if remove_outliers != None:
outliers_row = eval.outliers_category(data, data.columns, ratio=1.5, by="row")
remove = [n for n, i in enumerate(outliers_row) if i > remove_outliers]
data = data.drop(remove)
#data = data.reset_index()
print(data.head())
#if bal != None:
#data = balance(data, to_clf, bal,train_ratio, random_state)
if as_df:
return data
else:
data = split_dataset(data, to_clf, train_ratio, random_state)
return data
plt.show()
"""
#Redução piora um bocado
#%%
#df = datapp.subsample(data, to_clf)
trnX, tstX, valX, trnY, tstY, valY = datapp.subsample_split(
data, to_clf, categoric, "standard")
print(trnX.shape)
print(tstX.shape)
print(valX.shape)
#%%
outliers_col = eval.outliers_category(data,
data.columns.tolist(),
ratio=1.5,
by="column")
outliers_row = eval.outliers_category(data,
data.columns.tolist(),
ratio=1.5,
by="row")
plt.figure()
bin = 20
plt.hist(outliers_col, bin)
plt.title = "Frequencies of quantity of outliers (by column)"
plt.show()
plt.figure()
bin = 20
plt.hist(outliers_row, bin, cumulative=False)
plt.title = "Frequencies of quantity of outliers (by row)"
plt.show()