stats = Paragraph(text='', width=1000, name='Selected Features:')
y = df[df.columns[:1]].values.ravel()
df1 = df.drop(df.columns[:1], axis=1)
selector = SelectKBest(chi2, k=5).fit(df1, y)
X_new = selector.transform(df1)
mask = selector.get_support() #list of booleans
new_features = [] # The list of your K best features
for bool, feature in zip(mask, df.columns[1:].tolist()):
if bool:
new_features.append(feature)
#print(new_features)
features.value = new_features
stats.text = "Top 5 features according to Select K Best (Chi2) : " + str(
new_features)
x_train_original, x_test_original, y_train_original, y_test_original = train_test_split(
X_new, y, test_size=0.25)
#For standardizing data
#clf = svm.LinearSVC(random_state=0)
clf = RandomForestClassifier()
clf.fit(x_train_original, y_train_original)
predictions = clf.predict(x_test_original)
#print("Accuracy =", accuracy_score(y_test_original,predictions))
#print(np.unique(predictions))
tn, fp, fn, tp = confusion_matrix(y_test_original, predictions,
labels=[0, 1]).ravel()
def select_values_2(attr, old, new, w_box, c_data):
if new != 'None':
if c_data[w_box.children[1].
value][new].values.dtype == 'object': # categorical data
level_3 = MultiSelect(title='value',
value=['None'],
options=['None'],
width=180)
try:
level_3.options = np.unique(
c_data[w_box.children[1].value]
[new].iloc[:, 0].dropna().values).tolist()
level_3.value = [level_3.options[0]]
except TypeError:
level_3.options = np.unique([
str(obj) for obj in c_data[w_box.children[1].value]
[new].iloc[:, 0].dropna().values
]).tolist()
finally:
w_box.children[3] = column(level_3)
elif 'datetime' in str(c_data[w_box.children[1].value]
[new].values.dtype): # datetime data
start = c_data[w_box.children[1].value][new].min().dt.date.item()
end = c_data[w_box.children[1].value][new].max().dt.date.item()
date_slider = DateRangeSlider(
title="",
start=start,
end=end,
value=(start, end),
# value_as_date=True,
# step=1,
width=180)
checkbox_group = CheckboxGroup(labels=["invert selection"],
active=[],
width=180)
w_box.children[3] = column(date_slider, checkbox_group)
elif 'int' in str(c_data[w_box.children[1].value][new].values.dtype) or \
'float' in str(c_data[w_box.children[1].value][new].values.dtype):
# print("3 ", clinical_data[select_1.value][new].values.dtype)
start = c_data[w_box.children[1].value][new].min().item()
end = c_data[w_box.children[1].value][new].max().item()
slider = RangeSlider(start=start,
end=end,
step=0.1,
value=(start, end),
title=new + " Range",
width=180)
checkbox_group = CheckboxGroup(labels=["invert selection"],
active=[],
width=180)
w_box.children[3] = column(slider, checkbox_group)
else:
print(
"Something went wrong, unexpected datatype by clinical data value selecting"
) # TODO error message?
else:
w_box.children[3] = PreText(text='please select a property', width=200)