tommydangerous

import numpy

input_arr = numpy.array([
    [10, 20, 30],
    [40, 50, 60],
])

tommydangerous

# Load Numpy module
import numpy as np

# Creating a 1-D list (horizontal)
list1 = [2, 3, 5]

# Creating a 1-D list (vertical)
list2 = [
    [20],
    [30],

tommydangerous

baseline_accuracy_score = y_test.value_counts()[0] / len(y_test)

print(f'Model performance.  : {accuracy}')
print(f'Baseline performance: {baseline_accuracy_score}')

tommydangerous

from sklearn.metrics import accuracy_score

accuracy = accuracy_score(y_test, y_pred)
print(f'Accuracy score: {accuracy}')

tommydangerous

y_pred = classifier.predict(X_test)

tommydangerous

X_test = X_test_raw.copy()

# Add columns
X_test['can_vote'] = X_test['Age'].apply(lambda age: 1 if age >= 18 else 0)
X_test.loc[:, 'cabin_letter'] = X_test['Cabin'].apply(
    lambda cabin: cabin[0] if cabin and type(cabin) is str else None,
)

# Remove columns
X_test = X_test.drop(columns=['Name', 'PassengerId'])

tommydangerous

classifier.fit(X_train, y_train)

tommydangerous

from sklearn.linear_model import LogisticRegression

classifier = LogisticRegression(max_iter=10000)

tommydangerous

features_to_use = [
    'Age',
    'SibSp',
    'Parch',
    'Fare',
    'can_vote',
] + new_column_names
X_train = df[features_to_use].copy()

tommydangerous

from sklearn.preprocessing import OneHotEncoder

categorical_columns = ['Pclass', 'Sex', 'Embarked', 'cabin_letter']
categorical_encoder = OneHotEncoder(handle_unknown='ignore')
categorical_encoder.fit(df[categorical_columns])

# Add the new columns to the data
new_column_names = []
for idx, cat_column_name in enumerate(categorical_columns):
    values = categorical_encoder.categories_[idx]