# Generating a familysize column  titanic["FamilySize"] = titanic["SibSp"] + titanic["Parch"]    # The .apply method generates a new series  titanic["NameLength"] = titanic["Name"].apply(lambda x: len(x))  

import re      # A function to get the title from a name.  def get_title(name):      # Use a regular expression to search for a title.      # Titles always consist of capital and lowercase letters, and end with a period.      title_search = re.search(' ([A-Za-z]+).', name)      # If the title exists, extract and return it.      if title_search:          return title_search.group(1)      return ""      # Get all the titles and print how often each one occurs.  titles = titanic["Name"].apply(get_title)  print(pandas.value_counts(titles))    # Map each title to an integer.  Some titles are very rare, and are compressed into the same codes as other titles.  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  }  for k, v in title_mapping.items():      titles[titles == k] = v    # Verify that we converted everything.  # 验证我们是否转换了所有内容  print(pandas.value_counts(titles))    # Add in the title column.  titanic["Title"] = titles  

Mr          517  Miss        182  Mrs         125  Master       40  Dr            7  Rev           6  Major         2  Mlle          2  Col           2  Sir           1  Mme           1  Lady          1  Countess      1  Capt          1  Ms            1  Don           1  Jonkheer      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  

import numpy as np  from sklearn.feature_selection import SelectKBest, f_classif # 选择最好特征  import matplotlib.pyplot as plt  predictors = [      "Pclass", "Sex", "Age", "SibSp", "Parch", "Fare", "Embarked", "FamilySize",      "Title", "NameLength"  ]    # Perform feature selection  # 执行特征选择  selector = SelectKBest(f_classif, k=5)  selector.fit(titanic[predictors], titanic["Survived"])    # Get the raw p-values for each feature, and transform from p-values into scores  scores = -np.log10(selector.pvalues_)    # Plot the scores.  See how "Pclass", "Sex", "Title", and "Fare" are the best?  plt.bar(range(len(predictors)), scores)  plt.xticks(range(len(predictors)), predictors, rotation='vertical')  plt.show()    # Pick only the four best features.  # 只选择4个最好的特征  predictors = ["Pclass", "Sex", "Fare", "Title"]    alg = RandomForestClassifier(random_state=1,                               n_estimators=50,                               min_samples_split=8,                               min_samples_leaf=4)  

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,solver='liblinear'), ["Pclass", "Sex", "Fare", "FamilySize", "Title", "Age", "Embarked"]]  ]    # Initialize the cross validation folds  kf = KFold(n_splits=3,shuffle=False, random_state=1)    predictions = []  for train, test in kf.split(titanic):      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  # 两个分类器的平均结果      # 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.  # 将所有的预测放在一个数组中  predictions = np.concatenate(predictions, axis=0)    # Compute accuracy by comparing to the training data.  accuracy = sum(predictions == titanic["Survived"]) / len(predictions)  print(accuracy)  

0.8215488215488216  

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"]  

predictors = [      "Pclass", "Sex", "Age", "Fare", "Embarked", "FamilySize", "Title"  ]    algorithms = [      [          GradientBoostingClassifier(random_state=1,                                     n_estimators=25,                                     max_depth=3), predictors      ],      [          LogisticRegression(random_state=1, solver='liblinear'),          ["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]      predictions[predictions <= .5] = 0      predictions[predictions > .5] = 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