dradecic

def redraw(p_class):
    survived_chart = survived_bar_chart(df, p_class)
    title_chart = class_titles_bar_chart(df, p_class)
    hist_age = age_hist(df, p_class)
    return (
        survived_chart,
        title_chart,
        hist_age
    )

dradecic

@app.route('/', methods=['GET', 'POST'])
def chart():
    selected_class = request.form.get('dropdown-select')

    if selected_class == 0 or selected_class == None:
        survived_chart, title_chart, hist_age = redraw(1)
    else:
        survived_chart, title_chart, hist_age = redraw(selected_class)

    script_survived_chart, div_survived_chart = components(survived_chart)

dradecic

%matplotlib inline

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

import warnings
warnings.filterwarnings('ignore')
pd.options.display.max_columns = None

dradecic

data.drop(['Ticket', 'PassengerId'], axis=1, inplace=True)

gender_mapper = {'male': 0, 'female': 1}
data['Sex'].replace(gender_mapper, inplace=True)

data['Title'] = data['Name'].apply(lambda x: x.split(',')[1].strip().split(' ')[0])
data['Title'] = [0 if x in ['Mr.', 'Miss.', 'Mrs.'] else 1 for x in data['Title']]
data = data.rename(columns={'Title': 'Title_Unusual'})
data.drop('Name', axis=1, inplace=True)

dradecic

correlated_features = set()
correlation_matrix = data.drop('Survived', axis=1).corr()

for i in range(len(correlation_matrix.columns)):
    for j in range(i):
        if abs(correlation_matrix.iloc[i, j]) > 0.8:
            colname = correlation_matrix.columns[i]
            correlated_features.add(colname)

dradecic

X = data.drop('Survived', axis=1)
target = data['Survived']

rfc = RandomForestClassifier(random_state=101)
rfecv = RFECV(estimator=rfc, step=1, cv=StratifiedKFold(10), scoring='accuracy')
rfecv.fit(X, target)

dradecic

print('Optimal number of features: {}'.format(rfecv.n_features_))

dradecic

print(np.where(rfecv.support_ == False)[0])

X.drop(X.columns[np.where(rfecv.support_ == False)[0]], axis=1, inplace=True)

dradecic

dset = pd.DataFrame()
dset['attr'] = X.columns
dset['importance'] = rfecv.estimator_.feature_importances_

dset = dset.sort_values(by='importance', ascending=False)


plt.figure(figsize=(16, 14))
plt.barh(y=dset['attr'], width=dset['importance'], color='#1976D2')
plt.title('RFECV - Feature Importances', fontsize=20, fontweight='bold', pad=20)

dradecic

plt.figure(figsize=(16, 9))
plt.title('Recursive Feature Elimination with Cross-Validation', fontsize=18, fontweight='bold', pad=20)
plt.xlabel('Number of features selected', fontsize=14, labelpad=20)
plt.ylabel('% Correct Classification', fontsize=14, labelpad=20)
plt.plot(range(1, len(rfecv.grid_scores_) + 1), rfecv.grid_scores_, color='#303F9F', linewidth=3)

plt.show()