print (titanic["Sex"].unique())
# Replace all the occurences of male with the number 0.
titanic.loc[titanic["Sex"] == "male", "Sex"] = 0
titanic.loc[titanic["Sex"] == "female", "Sex"] = 1
複製程式碼
# 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.model_selection import KFold
# 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(n_splits=3, random_state=1, shuffle=False)
predictions = []
for train, test in kf.split(titanic):
# 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)
import numpy as np
# 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)
0.2615039281705948
複製程式碼
from sklearn.model_selection import cross_val_score
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_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())
0.7878787878787877
複製程式碼
隨機森林測試
import pandas #ipython notebook
import numpy as np
from sklearn.model_selection import KFold
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import RandomForestClassifier
titanic_test = pandas.read_csv("C:\\ML\\MLData\\titanic_train.csv")
titanic_test["Age"] = titanic_test["Age"].fillna(titanic_test["Age"].median())
titanic_test["Fare"] = titanic_test["Fare"].fillna(titanic_test["Fare"].median())
titanic_test.loc[titanic_test["Sex"] == "male", "Sex"] = 0
titanic_test.loc[titanic_test["Sex"] == "female", "Sex"] = 1
titanic_test["Embarked"] = titanic_test["Embarked"].fillna("S")
titanic_test.loc[titanic_test["Embarked"] == "S", "Embarked"] = 0
titanic_test.loc[titanic_test["Embarked"] == "C", "Embarked"] = 1
titanic_test.loc[titanic_test["Embarked"] == "Q", "Embarked"] = 2
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=50, 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 = KFold(n_splits=3, random_state=1, shuffle=False)
scores = cross_val_score(alg, titanic_test[predictors], titanic_test["Survived"], cv=kf)
0.7901234567901234
複製程式碼
資料預處理
# Take the mean of the scores (because we have one for each fold)
print(scores.mean())
# Generating a familysize column
titanic_test["FamilySize"] = titanic_test["SibSp"] + titanic_test["Parch"]
# The .apply method generates a new series
titanic_test["NameLength"] = titanic_test["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_test["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.
print(pandas.value_counts(titles))
# Add in the title column.
titanic_test["Title"] = titles
Mr 517
Miss 182
Mrs 125
Master 40
Dr 7
Rev 6
Major 2
Col 2
Mlle 2
Don 1
Capt 1
Ms 1
Jonkheer 1
Countess 1
Sir 1
Mme 1
Lady 1
複製程式碼
def plot_corr(df,size=10):
'''Function plots a graphical correlation matrix for each pair of columns in the dataframe.
Input:
df: pandas DataFrame
size: vertical and horizontal size of the plot'''
corr = df.corr()
fig, ax = plt.subplots(figsize=(size, size))
ax.matshow(corr)
for (i, j), z in np.ndenumerate(corr):
ax.text(j, i, '{:.2f}'.format(z), ha='center', va='center')
plt.xticks(range(len(corr.columns)), corr.columns)
plt.yticks(range(len(corr.columns)), corr.columns)
# 特徵相關性圖表
plot_corr(df)
複製程式碼
多特徵隨機森林測試（增加訓練特徵）
import numpy as np
from sklearn.feature_selection import SelectKBest, f_classif
import matplotlib.pyplot as plt
predictors = ["Pclass", "Sex", "Age", "SibSp", "Parch", "Fare", "Embarked", "FamilySize", "Title", "NameLength"]
# Perform feature selection
selector = SelectKBest(f_classif, k=5)
selector.fit(titanic_test[predictors], titanic_test["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.
predictors = ["Pclass", "Sex", "Fare", "Title"]
# 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=50, 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 = KFold(n_splits=3, random_state=1, shuffle=False)
scores = cross_val_score(alg, titanic_test[predictors], titanic_test["Survived"], cv=kf)
# Take the mean of the scores (because we have one for each fold)
print(scores.mean())
複製程式碼
from sklearn.tree import DecisionTreeClassifier
# 1.criterion gini or entropy（基於gini係數和熵值來指定）
# 2.splitter best or random 前者是在所有特徵中找最好的切分點 後者是在部分特徵中（資料量大的時候）
# 3.max_features None（所有） 特徵小於50的時候一般使用所有的 ，log2，sqrt，N
# 4.max_depth 資料少或者特徵少的時候可以不管這個值，如果模型樣本量多，特徵也多的情況下，可以嘗試限制下
# 5.min_samples_split 如果某節點的樣本數少於min_samples_split，則不會繼續再嘗試選擇最優特徵來進行劃分
# 如果樣本量不大，不需要管這個值。如果樣本量數量級非常大，則推薦增大這個值。
# 6.min_samples_leaf 這個值限制了葉子節點最少的樣本數，如果某葉子節點數目小於樣本數，則會和兄弟節點一起被
# 剪枝，如果樣本量不大，不需要管這個值，大些如10W可是嘗試下5
# 7.min_weight_fraction_leaf 這個值限制了葉子節點所有樣本權重和的最小值，如果小於這個值，則會和兄弟節點一起
# 被剪枝預設是0，就是不考慮權重問題。一般來說，如果我們有較多樣本有缺失值，
# 或者分類樹樣本的分佈類別偏差很大，就會引入樣本權重，這時我們就要注意這個值了。
# 8.max_leaf_nodes 通過限制最大葉子節點數，可以防止過擬合，預設是"None”，即不限制最大的葉子節點數。
# 如果加了限制，演算法會建立在最大葉子節點數內最優的決策樹。
# 如果特徵不多，可以不考慮這個值，但是如果特徵分成多的話，可以加以限制
# 具體的值可以通過交叉驗證得到。
# 9.class_weight 指定樣本各類別的的權重，主要是為了防止訓練集某些類別的樣本過多
# 導致訓練的決策樹過於偏向這些類別。這裡可以自己指定各個樣本的權重
# 如果使用“balanced”，則演算法會自己計算權重，樣本量少的類別所對應的樣本權重會高。
# 10.min_impurity_split 這個值限制了決策樹的增長，如果某節點的不純度
# (基尼係數，資訊增益，均方差，絕對差)小於這個閾值
# 則該節點不再生成子節點。即為葉子節點 。
decision_tree_classifier = DecisionTreeClassifier()
# Train the classifier on the training set
decision_tree_classifier.fit(training_inputs, training_classes)
# Validate the classifier on the testing set using classification accuracy
decision_tree_classifier.score(testing_inputs, testing_classes)
複製程式碼
級聯預測
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.linear_model import LogisticRegression
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=50, max_depth=5), ["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(n_splits=3, random_state=1, shuffle=False)
predictions = []
for train, test in kf.split(titanic_test):
train_target = titanic_test["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_test[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_test[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_test["Survived"]]) / len(predictions)
print(accuracy)
複製程式碼