python 火车测试拆分

Posted 2021-05-09

# Import libraries necessary for this project
import numpy as np
import pandas as pd
from IPython.display import display # Allows the use of display() for DataFrames

# Pretty display for notebooks
%matplotlib inline

# Set a random seed
import random
random.seed(42)

# Load the dataset
in_file = 'titanic_data.csv'
full_data = pd.read_csv(in_file)

# Print the first few entries of the RMS Titanic data
display(full_data.head())

# Store the 'Survived' feature in a new variable and remove it from the dataset
outcomes = full_data['Survived']
features_raw = full_data.drop('Survived', axis = 1)

# Show the new dataset with 'Survived' removed
display(features_raw.head())

features = pd.get_dummies(features_raw)
features = features.fillna(0.0)
display(features.head())

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(features, outcomes, test_size=0.2, random_state=42)

# Import the classifier from sklearn
from sklearn.tree import DecisionTreeClassifier

# TODO: Define the classifier, and fit it to the data
model = DecisionTreeClassifier()
model.fit(X_train, y_train)

# prints:
DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')

# Making predictions
y_train_pred = model.predict(X_train)
y_test_pred = model.predict(X_test)

# Calculate the accuracy
from sklearn.metrics import accuracy_score
train_accuracy = accuracy_score(y_train, y_train_pred)
test_accuracy = accuracy_score(y_test, y_test_pred)
print('The training accuracy is', train_accuracy)
print('The test accuracy is', test_accuracy)

# Then repeat for hyper parameters
# TODO: Train the model
model = DecisionTreeClassifier(max_depth=10, min_samples_leaf=6, min_samples_split=4)
model.fit(X_train, y_train)

# TODO: Make predictions
y_train_pred = model.predict(X_train)
y_test_pred = model.predict(X_test)

# TODO: Calculate the accuracy
train_accuracy = accuracy_score(y_train, y_train_pred)
test_accuracy = accuracy_score(y_test, y_test_pred)
print('The training accuracy is', train_accuracy)
print('The test accuracy is', test_accuracy)