female = [[30, 1, 0, 1, 0, 0]]

https://colab.research.google.com/github/
jeffprosise/Machine-Learning/blob/master/
Titanic%20(Logistic%20Regression).ipynb

import pandas as pd

url = ("https://raw.githubusercontent.com/"
       "jeffprosise/Machine-Learning/master/Data/titanic.csv")
df = pd.read_csv(url)      # 891 rows, 12 columns

df = df[['Survived', 'Age', 'Sex', 'Pclass']]
df = pd.get_dummies(df, columns=['Sex', 'Pclass'])
df.dropna(inplace=True)      # 714 rows remain

x = df.drop('Survived', axis=1)
y = df['Survived']
x_train, x_test, y_train, y_test = train_test_split(
    x, y, test_size=0.2, stratify=y, random_state=0)

model = LogisticRegression(random_state=0)
model.fit(x_train, y_train)
model.score(x_test, y_test)          # 0.8322

              precision    recall  f1-score   support

           0       0.82      0.92      0.87        85
           1       0.85      0.71      0.77        58

    accuracy                           0.83       143
   macro avg       0.84      0.81      0.82       143
weighted avg       0.83      0.83      0.83       143

https://colab.research.google.com/github/
tirthajyoti/Machine-Learning-with-Python/blob/master/
Classification/Logistic_Regression_Classification.ipynb

url = ("https://raw.githubusercontent.com/tirthajyoti/"
       "Machine-Learning-with-Python/master/Datasets/titanic_train.csv")
train = pd.read_csv(url)      # the same 891 rows

a = list(train.groupby('Pclass')['Age'].mean())
def impute_age(cols):
    Age = cols['Age']
    Pclass = cols['Pclass']
    if pd.isnull(Age):
        if Pclass == 1:
            return a[0]
        elif Pclass == 2:
            return a[1]
        else:
            return a[2]
    else:
        return Age
train['Age'] = train[['Age', 'Pclass']].apply(impute_age, axis=1)

train.drop('Cabin', axis=1, inplace=True)
train.dropna(inplace=True)                 # 889 rows
train.drop(['PassengerId', 'Name', 'Ticket'], axis=1, inplace=True)

sex = pd.get_dummies(train['Sex'], drop_first=True)
embark = pd.get_dummies(train['Embarked'], drop_first=True)
train.drop(['Sex', 'Embarked'], axis=1, inplace=True)
train = pd.concat([train, sex, embark], axis=1)