模型评估---交叉验证

# Import the linear regression class
from sklearn.linear_model import LinearRegression
# Sklearn also has a helper that makes it easy to do cross validation
from sklearn.cross_validation import KFold
import numpy as np

# The columns we‘ll use to predict the target
predictors = ["Pclass", "Sex", "Age", "SibSp", "Parch", "Fare", "Embarked"]

# Initialize our algorithm class
alg = LinearRegression()
# Generate cross validation folds for the titanic dataset.  It return the row indices corresponding to train and test.
# We set random_state to ensure we get the same splits every time we run this.
kf = KFold(titanic.shape[0], n_folds=3, random_state=1)

predictions = []
for train, test in kf:
    # The predictors we‘re using the train the algorithm.  Note how we only take the rows in the train folds.
    train_predictors = (titanic[predictors].iloc[train,:])
    # The target we‘re using to train the algorithm.
    train_target = titanic["Survived"].iloc[train]
    # Training the algorithm using the predictors and target.
    alg.fit(train_predictors, train_target)
    # We can now make predictions on the test fold
    test_predictions = alg.predict(titanic[predictors].iloc[test,:])
    predictions.append(test_predictions)


# The predictions are in three separate numpy arrays.  Concatenate them into one.  
# We concatenate them on axis 0, as they only have one axis.
predictions = np.concatenate(predictions, axis=0)

# Map predictions to outcomes (only possible outcomes are 1 and 0)
predictions[predictions > .5] = 1
predictions[predictions <=.5] = 0
accuracy = sum(predictions[predictions == titanic["Survived"]]) / len(predictions)
print accuracy

from sklearn import cross_validation
from sklearn.linear_model import LogisticRegression
# Initialize our algorithm
alg = LogisticRegression(random_state=1)
# Compute the accuracy score for all the cross validation folds.  (much simpler than what we did before!)
scores = cross_validation.cross_val_score(alg, titanic[predictors], titanic["Survived"], cv=3)
# Take the mean of the scores (because we have one for each fold)
print(scores.mean())

from sklearn import cross_validation
from sklearn.ensemble import RandomForestClassifier

predictors = ["Pclass", "Sex", "Age", "SibSp", "Parch", "Fare", "Embarked"]

# Initialize our algorithm with the default paramters
# n_estimators is the number of trees we want to make
# min_samples_split is the minimum number of rows we need to make a split
# min_samples_leaf is the minimum number of samples we can have at the place where a tree branch ends (the bottom points of the tree)
alg = RandomForestClassifier(random_state=1, n_estimators=10, min_samples_split=2, min_samples_leaf=1)
# Compute the accuracy score for all the cross validation folds.  (much simpler than what we did before!)
kf = cross_validation.KFold(titanic.shape[0], n_folds=3, random_state=1)
scores = cross_validation.cross_val_score(alg, titanic[predictors], titanic["Survived"], cv=kf)

# Take the mean of the scores (because we have one for each fold)
print(scores.mean())

predictors = ["Pclass", "Sex", "Age", "Fare", "Embarked", "FamilySize", "Title"]

algorithms = [
    [GradientBoostingClassifier(random_state=1, n_estimators=25, max_depth=3), predictors],
    [LogisticRegression(random_state=1), ["Pclass", "Sex", "Fare", "FamilySize", "Title", "Age", "Embarked"]]
]

full_predictions = []
for alg, predictors in algorithms:
    # Fit the algorithm using the full training data.
    alg.fit(titanic[predictors], titanic["Survived"])
    # Predict using the test dataset.  We have to convert all the columns to floats to avoid an error.
    predictions = alg.predict_proba(titanic_test[predictors].astype(float))[:,1]
    full_predictions.append(predictions)

# The gradient boosting classifier generates better predictions, so we weight it higher.
predictions = (full_predictions[0] * 3 + full_predictions[1]) / 4
predictions

from sklearn.ensemble import GradientBoostingClassifier
import numpy as np

# The algorithms we want to ensemble.
# We‘re using the more linear predictors for the logistic regression, and everything with the gradient boosting classifier.
algorithms = [
    [GradientBoostingClassifier(random_state=1, n_estimators=25, max_depth=3), ["Pclass", "Sex", "Age", "Fare", "Embarked", "FamilySize", "Title",]],
    [LogisticRegression(random_state=1), ["Pclass", "Sex", "Fare", "FamilySize", "Title", "Age", "Embarked"]]
]

# Initialize the cross validation folds
kf = KFold(titanic.shape[0], n_folds=3, random_state=1)

predictions = []
for train, test in kf:
    train_target = titanic["Survived"].iloc[train]
    full_test_predictions = []
    # Make predictions for each algorithm on each fold
    for alg, predictors in algorithms:
        # Fit the algorithm on the training data.
        alg.fit(titanic[predictors].iloc[train,:], train_target)
        # Select and predict on the test fold.  
        # The .astype(float) is necessary to convert the dataframe to all floats and avoid an sklearn error.
        test_predictions = alg.predict_proba(titanic[predictors].iloc[test,:].astype(float))[:,1]
        full_test_predictions.append(test_predictions)
    # Use a simple ensembling scheme -- just average the predictions to get the final classification.
    test_predictions = (full_test_predictions[0] + full_test_predictions[1]) / 2
    # Any value over .5 is assumed to be a 1 prediction, and below .5 is a 0 prediction.
    test_predictions[test_predictions <= .5] = 0
    test_predictions[test_predictions > .5] = 1
    predictions.append(test_predictions)

# Put all the predictions together into one array.
predictions = np.concatenate(predictions, axis=0)

# Compute accuracy by comparing to the training data.
accuracy = sum(predictions[predictions == titanic["Survived"]]) / len(predictions)
print(accuracy)