用pandas加载数据:
import pandas as pd
import numpy as np
from pandas import Series,DataFrame
data_train = pd.read_csv("train.csv")
data_train.columns
data_train.info()
上面数据告诉我们，训练数据中总共有891名乘客，但是很不幸，我们有些属性的数据不全.
data_train.describe()
import matplotlib.pyplot as plt
from pylab import mpl
fig = plt.figure()
fig.set(alpha=0.2) # 设定图表颜色alpha参数
plt.subplot2grid((3,2),(0,0)) # 在一张大图里分列几个小图
data_train.Survived.value_counts().plot(kind='bar')# 条形图获救与否
plt.title(u"survived") # 1表示获救
plt.ylabel(u"number")
plt.subplot2grid((3,2),(0,1))
data_train.Pclass.value_counts().plot(kind="bar")
plt.ylabel(u"number")
plt.title(u"pclass")
plt.subplot2grid((3,2),(1,0))
plt.scatter(data_train.Survived, data_train.Age)
plt.ylabel(u"age") # sets the y axis lable
plt.grid(b=True, which='major', axis='y') # formats the grid line style of our graphs
plt.title(u"age & survived") #1表示获救
plt.subplot2grid((3,2),(1,1), colspan=2)
data_train.Age[data_train.Pclass == 1].plot(kind='kde') # plots a kernel desnsity estimate of the subset of the 1st class passanges's age
data_train.Age[data_train.Pclass == 2].plot(kind='kde')
data_train.Age[data_train.Pclass == 3].plot(kind='kde')
plt.xlabel(u"年龄")# plots an axis lable
plt.ylabel(u"密度")
plt.title(u"各等级的乘客年龄分布")
plt.legend((u'头等舱', u'2等舱',u'3等舱'),loc='best') # sets our legend for our graph.
plt.subplot2grid((3,2),(2,0))
data_train.Embarked.value_counts().plot(kind='bar')
plt.title(u"各登船口岸上船人数")
plt.ylabel(u"人数")
plt.show()
#看看各乘客等级的获救情况
fig = plt.figure()
fig.set(alpha=0.2) # 设定图表颜色alpha参数
Survived_0 = data_train.Pclass[data_train.Survived == 0].value_counts()
Survived_1 = data_train.Pclass[data_train.Survived == 1].value_counts()
df=pd.DataFrame({'Survived_1':Survived_1, 'Survived_0':Survived_0})
df.plot(kind='bar')
plt.title("Survived")
plt.xlabel('pclass')
plt.ylabel("number")
plt.show()
``
#看看各登录港口的获救情况
fig = plt.figure()
fig.set(alpha=0.2) # 设定图表颜色alpha参数
Survived_0 = data_train.Embarked[data_train.Survived == 0].value_counts()
Survived_1 = data_train.Embarked[data_train.Survived == 1].value_counts()
df=pd.DataFrame({u'Survived_1':Survived_1, u'Survived_0':Survived_0})
df.plot(kind='bar')
plt.xlabel(u"Embarked")
plt.ylabel(u"number")
plt.show()
#看看各性别的获救情况
Survived_male = data_train.Survived[data_train.Sex == 'male'].value_counts()
Survived_female = data_train.Survived[data_train.Sex == 'female'].value_counts()
df = pd.DataFrame({'male':Survived_male, 'female':Survived_female})
df.plot(kind='bar')
plt.xlabel('sex')
plt.ylabel('number')
#然后我们再来看看各种舱级别情况下各性别的获救情况
fig=plt.figure()
fig.set(alpha=0.65) # 设置图像透明度，无所谓
plt.title(u"pclass and sex")
plt.subplot(221)
data_train.Survived[data_train.Sex == 'female'][data_train.Pclass != 3].value_counts().plot(kind='bar')
plt.xlabel('female in 12class')
plt.ylabel('number')
plt.subplot(222)
data_train.Survived[data_train.Sex == 'male'][data_train.Pclass != 3].value_counts().plot(kind='bar')
plt.xlabel('male in 12class')
plt.ylabel('number')
plt.subplot(223)
data_train.Survived[data_train.Sex == 'male'][data_train.Pclass == 3].value_counts().plot(kind='bar')
plt.xlabel('female in 3class')
plt.ylabel('number')
plt.subplot(224)
data_train.Survived[data_train.Sex == 'male'][data_train.Pclass == 3].value_counts().plot(kind='bar')
plt.xlabel('male in 3class')
plt.ylabel('number')
plt.show()
#那堂兄弟和父母呢？大家族会有优势么？
g = data_train.groupby(['SibSp','Survived'])
df = pd.DataFrame(g.count()['PassengerId'])
df
g = data_train.groupby(['Parch','Survived'])
df = pd.DataFrame(g.count()['PassengerId'])
df
#ticket是船票编号，应该是unique的，和最后的结果没有太大的关系，不纳入考虑的特征范畴
#cabin只有204个乘客有值，我们先看看它的一个分布
data_train.Cabin.value_counts()
Survived_cabin = data_train.Survived[pd.notnull(data_train.Cabin)].value_counts()
Survived_nocabin = data_train.Survived[pd.isnull(data_train.Cabin)].value_counts()
df = pd.DataFrame({'have':Survived_cabin, 'not have':Survived_nocabin})
df.plot(kind='bar',stacked=True)
plt.show()
似乎有cabin记录的乘客survival比例稍高，那先试试把这个值分为两类，有cabin值/无cabin值，一会儿加到类别特征好了.
通常遇到缺值的情况，我们会有几种常见的处理方式:
如果缺值的样本占总数比例极高，我们可能就直接舍弃了，作为特征加入的话，可能反倒带入noise，影响最后的结果了.
如果缺值的样本适中，而该属性非连续值特征属性(比如说类目属性)，那就把NaN作为一个新类别，加到类别特征中.
如果缺值的样本适中，而该属性为连续值特征属性，有时候我们会考虑给定一个step(比如这里的age，我们可以考虑每隔2/3岁为一个步长)，然后把它离散化，之后把NaN作为一个type加到属性类目中。
有些情况下，缺失的值个数并不是特别多，那我们也可以试着根据已有的值，拟合一下数据，补充上。
我们这里用scikit-learn中的RandomForest来拟合一下缺失的年龄数据
from sklearn.ensemble import RandomForestRegressor
def set_miss_ages(df):
age_df = df[['Age','Fare', 'Parch', 'SibSp', 'Pclass']]
known_age = age_df[age_df.Age.notnull()].as_matrix()
unknown_age = age_df[age_df.Age.isnull()].as_matrix()
y = known_age[:, 0]
X = known_age[:, 1:]
rf = RandomForestRegressor(random_state=0, n_estimators=2000, n_jobs=-1)
rf.fit(X, y)
predictedAge = rf.predict(unknown_age[:, 1:])
df.loc[(df.Age.isnull()), 'Age'] = predictedAge
return df ,rf
def set_Cabin_type(df):
df.loc[(df.Cabin.notnull()), 'Cabin'] = 'YES'
df.loc[(df.Cabin.isnull()), 'Cabin'] = 'NO'
return df
data_train, rf = set_miss_ages(data_train)
data_train = set_Cabin_type(data_train)
data_train
因为逻辑回归建模时，需要输入的特征都是数值型特征，我们通常会先对类目型的特征因子化/one-hot编码。
dummies_Cabin = pd.get_dummies(data_train['Cabin'], prefix= 'Cabin')
dummies_Embarked = pd.get_dummies(data_train['Embarked'], prefix='Embarked')
dummies_Sex = pd.get_dummies(data_train['Sex'], prefix='Sex')
dummies_Pclass = pd.get_dummies(data_train['Pclass'], prefix='Pclass')
df = pd.concat([data_train, dummies_Cabin, dummies_Embarked, dummies_Sex, dummies_Pclass], axis=1)
df.drop(['Pclass', 'Name', 'Sex', 'Ticket', 'Cabin', 'Embarked'], axis=1, inplace=True)
df.head(5)
接下来我们要接着做一些数据预处理的工作，比如scaling，将一些变化幅度较大的特征化到[-1,1]之内.这样可以加速logistic regression的收敛
import sklearn.preprocessing as preprocessing
scaler = preprocessing.StandardScaler()
age_scale_param = scaler.fit(df['Age'])
df['Age_scaled'] = scaler.fit_transform(df['Age'], age_scale_param)
fare_scale_param = scaler.fit(df['Fare'])
df['Fare_scaled'] = scaler.fit_transform(df['Fare'], fare_scale_param)
我们把需要的feature字段取出来，转成numpy格式，使用scikit-learn中的LogisticRegression建模
from sklearn import linear_model
train_df = df.filter(regex='Survived|Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass_.*')
train_np = train_df.as_matrix()
# y即Survival结果
y = train_np[:, 0]
# X即特征属性值
X = train_np[:, 1:]
# fit到RandomForestRegressor之中
clf = linear_model.LogisticRegression(C=1.0, penalty='l1', tol=1e-6)
clf.fit(X, y)
clf
接下来咱们对训练集和测试集做一样的操作
data_test = pd.read_csv("test.csv")
data_test.loc[ (data_test.Fare.isnull()), 'Fare' ] = 0
# 接着我们对test_data做和train_data中一致的特征变换
# 首先用同样的RandomForestRegressor模型填上丢失的年龄
tmp_df = data_test[['Age','Fare', 'Parch', 'SibSp', 'Pclass']]
null_age = tmp_df[data_test.Age.isnull()].as_matrix()
# 根据特征属性X预测年龄并补上
X = null_age[:, 1:]
predictedAges = rf.predict(X)
data_test.loc[ (data_test.Age.isnull()), 'Age' ] = predictedAges
data_test = set_Cabin_type(data_test)
dummies_Cabin = pd.get_dummies(data_test['Cabin'], prefix= 'Cabin')
dummies_Embarked = pd.get_dummies(data_test['Embarked'], prefix= 'Embarked')
dummies_Sex = pd.get_dummies(data_test['Sex'], prefix= 'Sex')
dummies_Pclass = pd.get_dummies(data_test['Pclass'], prefix= 'Pclass')
df_test = pd.concat([data_test, dummies_Cabin, dummies_Embarked, dummies_Sex, dummies_Pclass], axis=1)
df_test.drop(['Pclass', 'Name', 'Sex', 'Ticket', 'Cabin', 'Embarked'], axis=1, inplace=True)
df_test['Age_scaled'] = scaler.fit_transform(df_test['Age'], age_scale_param)
df_test['Fare_scaled'] = scaler.fit_transform(df_test['Fare'], fare_scale_param)
df_test
test = df_test.filter(regex='Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass_.*')
predictions = clf.predict(test)
result = pd.DataFrame({'PassengerId':data_test['PassengerId'].as_matrix(), 'Survived':predictions.astype(np.int32)})
result.to_csv("logistic_regression_predictions.csv", index=False)
0.76555，恩，结果还不错。毕竟，这只是我们简单分析过后出的一个baseline系统嘛.
我们用scikit-learn里面的learning_curve来帮我们分辨我们模型的状态>>>
import numpy as np
import matplotlib.pyplot as plt
from sklearn.learning_curve import learning_curve
# 用sklearn的learning_curve得到training_score和cv_score，使用matplotlib画出learning curve
def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None, n_jobs=1,
train_sizes=np.linspace(.05, 1., 20), verbose=0, plot=True):
"""
画出data在某模型上的learning curve.
参数解释
----------
estimator : 你用的分类器。
title : 表格的标题。
X : 输入的feature，numpy类型
y : 输入的target vector
ylim : tuple格式的(ymin, ymax), 设定图像中纵坐标的最低点和最高点
cv : 做cross-validation的时候，数据分成的份数，其中一份作为cv集，其余n-1份作为training(默认为3份)
n_jobs : 并行的的任务数(默认1)
"""
train_sizes, train_scores, test_scores = learning_curve(
estimator, X, y, cv=cv, n_jobs=n_jobs, train_sizes=train_sizes, verbose=verbose)
train_scores_mean = np.mean(train_scores, axis=1)
train_scores_std = np.std(train_scores, axis=1)
test_scores_mean = np.mean(test_scores, axis=1)
test_scores_std = np.std(test_scores, axis=1)
if plot:
plt.figure()
plt.title(title)
if ylim is not None:
plt.ylim(*ylim)
plt.xlabel(u"训练样本数")
plt.ylabel(u"得分")
plt.gca().invert_yaxis()
plt.grid()
plt.fill_between(train_sizes, train_scores_mean - train_scores_std, train_scores_mean + train_scores_std,
alpha=0.1, color="b")
plt.fill_between(train_sizes, test_scores_mean - test_scores_std, test_scores_mean + test_scores_std,
alpha=0.1, color="r")
plt.plot(train_sizes, train_scores_mean, 'o-', color="b", label=u"训练集上得分")
plt.plot(train_sizes, test_scores_mean, 'o-', color="r", label=u"交叉验证集上得分")
plt.legend(loc="best")
plt.draw()
plt.gca().invert_yaxis()
plt.show()
midpoint = ((train_scores_mean[-1] + train_scores_std[-1]) + (test_scores_mean[-1] - test_scores_std[-1])) / 2
diff = (train_scores_mean[-1] + train_scores_std[-1]) - (test_scores_mean[-1] - test_scores_std[-1])
return midpoint, diff
plot_learning_curve(clf, u"学习曲线", X, y)
接下来做交叉验证提升准确率:
from sklearn import cross_validation
# 简单看看打分情况
clf = linear_model.LogisticRegression(C=1.0, penalty='l1', tol=1e-6)
all_data = df.filter(regex='Survived|Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass_.*')
X = all_data.as_matrix()[:,1:]
y = all_data.as_matrix()[:,0]
print cross_validation.cross_val_score(clf, X, y, cv=5)
# 分割数据
split_train, split_cv = cross_validation.train_test_split(df, test_size=0.3, random_state=0)
train_df = split_train.filter(regex='Survived|Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass_.*')
# 生成模型
clf = linear_model.LogisticRegression(C=1.0, penalty='l1', tol=1e-6)
clf.fit(train_df.as_matrix()[:,1:], train_df.as_matrix()[:,0])
# 对cross validation数据进行预测
cv_df = split_cv.filter(regex='Survived|Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass_.*')
predictions = clf.predict(cv_df.as_matrix()[:,1:])
split_cv[ predictions != cv_df.as_matrix()[:,0] ].drop()
# 去除预测错误的case看原始dataframe数据
#split_cv['PredictResult'] = predictions
origin_data_train = pd.read_csv("Train.csv")
bad_cases = origin_data_train.loc[origin_data_train['PassengerId'].isin(split_cv[predictions != cv_df.as_matrix()[:,0]]['PassengerId'].values)]
bad_cases
data_train[data_train['Name'].str.contains("Major")]
data_train = pd.read_csv("train.csv")
data_train['Sex_Pclass'] = data_train.Sex + "_" + data_train.Pclass.map(str)
from sklearn.ensemble import RandomForestRegressor
### 使用 RandomForestClassifier 填补缺失的年龄属性
def set_missing_ages(df):
# 把已有的数值型特征取出来丢进Random Forest Regressor中
age_df = df[['Age','Fare', 'Parch', 'SibSp', 'Pclass']]
# 乘客分成已知年龄和未知年龄两部分
known_age = age_df[age_df.Age.notnull()].as_matrix()
unknown_age = age_df[age_df.Age.isnull()].as_matrix()
# y即目标年龄
y = known_age[:, 0]
# X即特征属性值
X = known_age[:, 1:]
# fit到RandomForestRegressor之中
rfr = RandomForestRegressor(random_state=0, n_estimators=2000, n_jobs=-1)
rfr.fit(X, y)
# 用得到的模型进行未知年龄结果预测
predictedAges = rfr.predict(unknown_age[:, 1::])
# 用得到的预测结果填补原缺失数据
df.loc[ (df.Age.isnull()), 'Age' ] = predictedAges
return df, rfr
def set_Cabin_type(df):
df.loc[ (df.Cabin.notnull()), 'Cabin' ] = "Yes"
df.loc[ (df.Cabin.isnull()), 'Cabin' ] = "No"
return df
data_train, rfr = set_missing_ages(data_train)
data_train = set_Cabin_type(data_train)
dummies_Cabin = pd.get_dummies(data_train['Cabin'], prefix= 'Cabin')
dummies_Embarked = pd.get_dummies(data_train['Embarked'], prefix= 'Embarked')
dummies_Sex = pd.get_dummies(data_train['Sex'], prefix= 'Sex')
dummies_Pclass = pd.get_dummies(data_train['Pclass'], prefix= 'Pclass')
dummies_Sex_Pclass = pd.get_dummies(data_train['Sex_Pclass'], prefix= 'Sex_Pclass')
df = pd.concat([data_train, dummies_Cabin, dummies_Embarked, dummies_Sex, dummies_Pclass, dummies_Sex_Pclass], axis=1)
df.drop(['Pclass', 'Name', 'Sex', 'Ticket', 'Cabin', 'Embarked', 'Sex_Pclass'], axis=1, inplace=True)
import sklearn.preprocessing as preprocessing
scaler = preprocessing.StandardScaler()
age_scale_param = scaler.fit(df['Age'])
df['Age_scaled'] = scaler.fit_transform(df['Age'], age_scale_param)
fare_scale_param = scaler.fit(df['Fare'])
df['Fare_scaled'] = scaler.fit_transform(df['Fare'], fare_scale_param)
from sklearn import linear_model
train_df = df.filter(regex='Survived|Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass.*')
train_np = train_df.as_matrix()
# y即Survival结果
y = train_np[:, 0]
# X即特征属性值
X = train_np[:, 1:]
# fit到RandomForestRegressor之中
clf = linear_model.LogisticRegression(C=1.0, penalty='l1', tol=1e-6)
clf.fit(X, y)
clf
data_test = pd.read_csv("test.csv")
data_test.loc[ (data_test.Fare.isnull()), 'Fare' ] = 0
data_test['Sex_Pclass'] = data_test.Sex + "_" + data_test.Pclass.map(str)
# 接着我们对test_data做和train_data中一致的特征变换
# 首先用同样的RandomForestRegressor模型填上丢失的年龄
tmp_df = data_test[['Age','Fare', 'Parch', 'SibSp', 'Pclass']]
null_age = tmp_df[data_test.Age.isnull()].as_matrix()
# 根据特征属性X预测年龄并补上
X = null_age[:, 1:]
predictedAges = rfr.predict(X)
data_test.loc[ (data_test.Age.isnull()), 'Age' ] = predictedAges
data_test = set_Cabin_type(data_test)
dummies_Cabin = pd.get_dummies(data_test['Cabin'], prefix= 'Cabin')
dummies_Embarked = pd.get_dummies(data_test['Embarked'], prefix= 'Embarked')
dummies_Sex = pd.get_dummies(data_test['Sex'], prefix= 'Sex')
dummies_Pclass = pd.get_dummies(data_test['Pclass'], prefix= 'Pclass')
dummies_Sex_Pclass = pd.get_dummies(data_test['Sex_Pclass'], prefix= 'Sex_Pclass')
df_test = pd.concat([data_test, dummies_Cabin, dummies_Embarked, dummies_Sex, dummies_Pclass, dummies_Sex_Pclass], axis=1)
df_test.drop(['Pclass', 'Name', 'Sex', 'Ticket', 'Cabin', 'Embarked', 'Sex_Pclass'], axis=1, inplace=True)
df_test['Age_scaled'] = scaler.fit_transform(df_test['Age'], age_scale_param)
df_test['Fare_scaled'] = scaler.fit_transform(df_test['Fare'], fare_scale_param)
df_test
test = df_test.filter(regex='Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass.*')
predictions = clf.predict(test)
result = pd.DataFrame({'PassengerId':data_test['PassengerId'].as_matrix(), 'Survived':predictions.astype(np.int32)})
result.to_csv("logistic_regression_predictions2.csv", index=False)
模型融合Bagging
from sklearn.ensemble import BaggingRegressor
train_df = df.filter(regex='Survived|Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass.*|Mother|Child|Family|Title')
train_np = train_df.as_matrix()
# y即Survival结果
y = train_np[:, 0]
# X即特征属性值
X = train_np[:, 1:]
# fit到BaggingRegressor之中
clf = linear_model.LogisticRegression(C=1.0, penalty='l1', tol=1e-6)
bagging_clf = BaggingRegressor(clf, n_estimators=10, max_samples=0.8, max_features=1.0, bootstrap=True, bootstrap_features=False, n_jobs=-1)
bagging_clf.fit(X, y)
test = df_test.filter(regex='Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass.*|Mother|Child|Family|Title')
predictions = bagging_clf.predict(test)
result = pd.DataFrame({'PassengerId':data_test['PassengerId'].as_matrix(), 'Survived':predictions.astype(np.int32)})
result.to_csv("./logistic_regression_predictions2.csv", index=False)
4033
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
