In [262]:
import pandas as pd #数据分析
import numpy as np #科学计算
from pandas import Series,DataFrame
import matplotlib.pyplot as plt
%matplotlib inline
data_train = pd.read_csv("./input/titanic/train.csv")
data_train.columns
Out[262]:
In [263]:
data_train.info()
In [264]:
data_train.describe()
Out[264]:
In [265]:
fig=plt.figure()
fig.set_alpha(0.5)
plt.subplot2grid((2,3),(0,0))
data_train.Survived.value_counts().plot(kind = 'bar')
plt.title(u'获救人数1为获救')
plt.ylabel(u'人数')
plt.subplot2grid((2,3),(0,1))
data_train.Pclass.value_counts().plot(kind='bar')
plt.title(u'乘客等级分布')
plt.ylabel(u'人数')
plt.subplot2grid((2,3),(0,2))
plt.scatter(data_train.Survived, data_train.Age)
plt.ylabel(u"年龄") # sets the y axis lable
plt.grid(b=True, which='major', axis='y') # formats the grid line style of our graphs
plt.title(u"按年龄看获救分布 (1为获救)")
plt.subplot2grid((2,3),(1,0), 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((2,3),(1,2))
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()
In [266]:
#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({u'获救':Survived_1, u'未获救':Survived_0})
df.plot(kind='bar', stacked=True)
plt.title(u"各乘客等级的获救情况")
plt.xlabel(u"乘客等级")
plt.ylabel(u"人数")
plt.show()
In [267]:
#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'获救':Survived_1, u'未获救':Survived_0})
df.plot(kind='bar', stacked=True)
plt.title(u"各登录港口乘客的获救情况")
plt.xlabel(u"登录港口")
plt.ylabel(u"人数")
plt.show()
In [268]:
#看看各性别的获救情况
fig = plt.figure()
fig.set(alpha=0.2) # 设定图表颜色alpha参数
Survived_m = data_train.Survived[data_train.Sex == 'male'].value_counts()
Survived_f = data_train.Survived[data_train.Sex == 'female'].value_counts()
df=pd.DataFrame({u'男性':Survived_m, u'女性':Survived_f})
df.plot(kind='bar', stacked=True)
plt.title(u"按性别看获救情况")
plt.xlabel(u"性别")
plt.ylabel(u"人数")
plt.show()
In [269]:
fig=plt.figure()
fig.set(alpha=0.65) # 设置图像透明度，无所谓
plt.title(u"根据舱等级和性别的获救情况")
ax1=fig.add_subplot(141)
data_train.Survived[data_train.Sex == 'female'][data_train.Pclass != 3].value_counts().plot(kind='bar', label="female highclass", color='#FA2479')
ax1.set_xticklabels([u"获救", u"未获救"], rotation=0)
ax1.legend([u"女性/高级舱"], loc='best')
ax2=fig.add_subplot(142, sharey=ax1)
data_train.Survived[data_train.Sex == 'female'][data_train.Pclass == 3].value_counts().plot(kind='bar', label='female, low class', color='pink')
ax2.set_xticklabels([u"未获救", u"获救"], rotation=0)
plt.legend([u"女性/低级舱"], loc='best')
ax3=fig.add_subplot(143, sharey=ax1)
data_train.Survived[data_train.Sex == 'male'][data_train.Pclass != 3].value_counts().plot(kind='bar', label='male, high class',color='lightblue')
ax3.set_xticklabels([u"未获救", u"获救"], rotation=0)
plt.legend([u"男性/高级舱"], loc='best')
ax4=fig.add_subplot(144, sharey=ax1)
data_train.Survived[data_train.Sex == 'male'][data_train.Pclass == 3].value_counts().plot(kind='bar', label='male low class', color='steelblue')
ax4.set_xticklabels([u"未获救", u"获救"], rotation=0)
plt.legend([u"男性/低级舱"], loc='best')
plt.show()
In [270]:
g = data_train.groupby(['SibSp','Survived'])
df = pd.DataFrame(g.count()['PassengerId'])
df
Out[270]:
In [271]:
g = data_train.groupby(['Parch','Survived'])
df = pd.DataFrame(g.count()['PassengerId'])
df
Out[271]:
In [272]:
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)
data_train
Out[272]:
In [273]:
# 因为逻辑回归建模时，需要输入的特征都是数值型特征
# 我们先对类目型的特征离散/因子化
# 以Cabin为例，原本一个属性维度，因为其取值可以是['yes','no']，而将其平展开为'Cabin_yes','Cabin_no'两个属性
# 原本Cabin取值为yes的，在此处的'Cabin_yes'下取值为1，在'Cabin_no'下取值为0
# 原本Cabin取值为no的，在此处的'Cabin_yes'下取值为0，在'Cabin_no'下取值为1
# 我们使用pandas的get_dummies来完成这个工作，并拼接在原来的data_train之上，如下所示
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
Out[273]:
In [274]:
# 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)
df
Out[274]:
In [275]:
# 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
Out[275]:
In [276]:
data_test = pd.read_csv("./input/titanic/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 = 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')
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
Out[276]:
In [277]:
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)
In [278]:
# BaseLine 系统构建完成
In [279]:
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
In [280]:
pd.DataFrame({"columns":list(train_df.columns)[1:], "coef":list(clf.coef_.T)})
Out[280]:
In [ ]:
from sklearn