Improving your submission

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)

kf = KFold(n_splits=3, random_state=1).split(titanic)
scores = model_selection.cross_val_score(alg, titanic[predictors], titanic["Survived"], cv=kf)
print(scores.mean())

alg2 = RandomForestClassifier(random_state=1, n_estimators=50, min_samples_split=4, min_samples_leaf=2)

scores2 = model_selection.cross_val_score(alg2, titanic[predictors], titanic["Survived"], cv=3)
print(scores2, scores2.mean())

Mr          517
Miss        182
Mrs         125
Master       40
Dr            7
Rev           6
Col           2
Major         2
Mlle          2
Countess      1
Ms            1
Lady          1
Jonkheer      1
Don           1
Mme           1
Capt          1
Sir           1
Name: Name, dtype: int64
1     517
2     183
3     125
4      40
5       7
6       6
7       5
10      3
8       3
9       2
Name: Name, dtype: int64

# Pick only the four best features.
predictors = ["Pclass", "Sex", "Fare", "Title"]

alg3 = RandomForestClassifier(random_state=1, n_estimators=50, min_samples_split=8, min_samples_leaf=4)

# Compute the accuracy score for all the cross validation folds.  (much simpler than what we did before!)
scores3 = model_selection.cross_val_score(alg3, titanic[predictors], titanic["Survived"], cv=3)

# Take the mean of the scores (because we have one for each fold)
print(scores3, scores3.mean())

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", "FamilyId"]],
    [LogisticRegression(random_state=1), ["Pclass", "Sex", "Fare", "FamilySize", "Title", "Age", "Embarked"]]
]

# Initialize the cross validation folds
kf = KFold(n_splits=3, random_state=1).split(titanic)

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 == titanic["Survived"]) / len(predictions)
print(accuracy)

# First, we'll add titles to the test set.
titles = titanic_test["Name"].apply(get_title)
# We're adding the Dona title to the mapping, because it's in the test set, but not the training set
title_mapping = {"Mr": 1, "Miss": 2, "Mrs": 3, "Master": 4, "Dr": 5, "Rev": 6, "Major": 7, "Col": 7, "Mlle": 8, "Mme": 8, "Don": 9, "Lady": 10, "Countess": 10, "Jonkheer": 10, "Sir": 9, "Capt": 7, "Ms": 2, "Dona": 10}
for k,v in title_mapping.items():
    titles[titles == k] = v
titanic_test["Title"] = titles
# Check the counts of each unique title.
print(pandas.value_counts(titanic_test["Title"]))

# Now, we add the family size column.
titanic_test["FamilySize"] = titanic_test["SibSp"] + titanic_test["Parch"]

# Now we can add family ids.
# We'll use the same ids that we did earlier.
print(family_id_mapping)

family_ids = titanic_test.apply(get_family_id, axis=1)
family_ids[titanic_test["FamilySize"] < 3] = -1
titanic_test["FamilyId"] = family_ids
titanic_test["NameLength"] = titanic_test["Name"].apply(lambda x: len(x))

submission.to_csv("kaggle2.csv", index=False)