Kaggle Titanic学习笔记知识点

1. 小提琴图。https://www.cnblogs.com/metafullstack/p/17658735.html

fig = plt.figure(figsize=(25, 7))
sns.violinplot(x='Sex', y='Age', 
               hue='Survived', data=data, 
               split=True,
               palette={0: "r", 1: "g"}
              )

2. 可以根据有逻辑关系的分组，来对缺失值进行填充。例如Age的缺失值根据Title、Sex、Pclass填充。

grouped_train = combined.iloc[:891].groupby(['Sex','Pclass','Title'])
grouped_median_train = grouped_train[['Age']].median()
grouped_median_train = grouped_median_train.reset_index()[['Sex', 'Pclass', 'Title', 'Age']]

def fill_age(row):
    condition = (
        (grouped_median_train['Sex'] == row['Sex']) & 
        (grouped_median_train['Title'] == row['Title']) & 
        (grouped_median_train['Pclass'] == row['Pclass'])
    ) 
    return grouped_median_train[condition]['Age'].values[0]

def process_age():
    global combined
    # a function that fills the missing values of the Age variable
    combined['Age'] = combined.apply(lambda row: fill_age(row) if np.isnan(row['Age']) else row['Age'], axis=1)
    status('age')
    return combined
    
combined = process_age()

3. 对于有特殊含义的缺失值，不应该直接删除，而是将其编码。例如Cabin。

train_cabin, test_cabin = set(), set()

for c in combined.iloc[:891]['Cabin']:
    try:
        train_cabin.add(c[0])
    except:
        train_cabin.add('U')
        
for c in combined.iloc[891:]['Cabin']:
    try:
        test_cabin.add(c[0])
    except:
        test_cabin.add('U')

def process_cabin():
    global combined    
    # replacing missing cabins with U (for Uknown)
    combined.Cabin.fillna('U', inplace=True)
    
    # mapping each Cabin value with the cabin letter
    combined['Cabin'] = combined['Cabin'].map(lambda c: c[0])
    
    # dummy encoding ...
    cabin_dummies = pd.get_dummies(combined['Cabin'], prefix='Cabin')    
    combined = pd.concat([combined, cabin_dummies], axis=1)

    combined.drop('Cabin', axis=1, inplace=True)
    status('cabin')
    return combined
combined = process_cabin()
combined.head()

4. 特征选择可以用随机森林的方法来进行特征选择。

# 这里是对特征重要性的可视化
clf = RandomForestClassifier(n_estimators=50, max_features='sqrt')
clf = clf.fit(train, targets)

features = pd.DataFrame()
features['feature'] = train.columns
features['importance'] = clf.feature_importances_
features.sort_values(by=['importance'], ascending=True, inplace=True)
features.set_index('feature', inplace=True)
features.plot(kind='barh', figsize=(25, 25))

# 这是将原数据的特征转换为选择后的特征
model = SelectFromModel(clf, prefit=True)
train_reduced = model.transform(train)
test_reduced = model.transform(test)

5. 自动地对模型进行调参（网格搜索法），并自动地根据选择的最佳参数建模的代码如下。

parameter_grid = {
                 'max_depth' : [4, 6, 8],
                 'n_estimators': [50, 10],
                 'max_features': ['sqrt', 'auto', 'log2'],
                 'min_samples_split': [2, 3, 10],
                 'min_samples_leaf': [1, 3, 10],
                 'bootstrap': [True, False],
                 }
forest = RandomForestClassifier()
cross_validation = StratifiedKFold(n_splits=5)

grid_search = GridSearchCV(forest,
                           scoring='accuracy',
                           param_grid=parameter_grid,
                           cv=cross_validation,
                           verbose=1
                          )

grid_search.fit(train, targets)
model = grid_search
parameters = grid_search.best_params_

print('Best score: {}'.format(grid_search.best_score_))
print('Best parameters: {}'.format(grid_search.best_params_))

parameters = grid_search.best_params_
    
model = RandomForestClassifier(**parameters)
model.fit(train, targets)

6. 模型可以集成起来运用。

trained_models = []
for model in models:
    model.fit(train, targets)
    trained_models.append(model)

predictions = []
for model in trained_models:
    predictions.append(model.predict_proba(test)[:, 1])

predictions_df = pd.DataFrame(predictions).T
predictions_df['out'] = predictions_df.mean(axis=1)
predictions_df['PassengerId'] = aux['PassengerId']
predictions_df['out'] = predictions_df['out'].map(lambda s: 1 if s >= 0.5 else 0)

predictions_df = predictions_df[['PassengerId', 'out']]
predictions_df.columns = ['PassengerId', 'Survived']