當前位置：首頁 > 编程资源 > 编程问答 >内容正文

编程问答

泰坦尼克号项目

發布時間：2024/3/12 编程问答 25 豆豆

生活随笔收集整理的這篇文章主要介紹了泰坦尼克号项目小編覺得挺不錯的,現在分享給大家,幫大家做個參考.

import pandas as pd df_train,df_test = pd.read_csv("F:/Python CODE/Kaggle_Titanic/train.csv"),pd.read_csv("F:/Python CODE/Kaggle_Titanic/test.csv") In?[2]: df_train.head()#查看表格的后5行 Out[2]: ?PassengerIdSurvivedPclassNameSexAgeSibSpParchTicketFareCabinEmbarked01234

1	0	3	Braund, Mr. Owen Harris	male	22.0	1	A/5 21171	7.2500	NaN	S
2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	PC 17599	71.2833	C85	C
3	1	3	Heikkinen, Miss. Laina	female	26.0	0	STON/O2. 3101282	7.9250	NaN	S
4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	113803	53.1000	C123	S
5	0	3	Allen, Mr. William Henry	male	35.0	0	373450	8.0500	NaN	S

SibSp -- 同船配偶以及兄弟姐妹的人數

Parch -- 同船父母或者子女的人數

Ticket -- 船票

Fare -- 票價

Cabin -- 艙位

Embarked -- 登船港口

In?[3]: df_train.info() #查看數據表的整體信息 <class 'pandas.core.frame.DataFrame'> RangeIndex: 891 entries, 0 to 890 Data columns (total 12 columns): PassengerId 891 non-null int64 Survived 891 non-null int64 Pclass 891 non-null int64 Name 891 non-null object Sex 891 non-null object Age 714 non-null float64 SibSp 891 non-null int64 Parch 891 non-null int64 Ticket 891 non-null object Fare 891 non-null float64 Cabin 204 non-null object Embarked 889 non-null object dtypes: float64(2), int64(5), object(5) memory usage: 83.6+ KB In?[4]: df_train.describe() #描述性統計 Out[4]: ?PassengerIdSurvivedPclassAgeSibSpParchFarecountmeanstdmin25%50%75%max

891.000000	891.000000	891.000000	714.000000	891.000000	891.000000	891.000000
446.000000	0.383838	2.308642	29.699118	0.523008	0.381594	32.204208
257.353842	0.486592	0.836071	14.526497	1.102743	0.806057	49.693429
1.000000	0.000000	1.000000	0.420000	0.000000	0.000000	0.000000
223.500000	0.000000	2.000000	20.125000	0.000000	0.000000	7.910400
446.000000	0.000000	3.000000	28.000000	0.000000	0.000000	14.454200
668.500000	1.000000	3.000000	38.000000	1.000000	0.000000	31.000000
891.000000	1.000000	3.000000	80.000000	8.000000	6.000000	512.329200

In?[5]: df_train[["Name","Sex","Ticket","Cabin","Embarked"]].describe()#對于object類型（python對象）同樣用describe（）處理 Out[5]: ?NameSexTicketCabinEmbarkedcountuniquetopfreq

891	891	891	204	889
891	2	681	147	3
Green, Mr. George Henry	male	CA. 2343	G6	S
1	577	7	4	644

In?[6]: #特征分析，在11個特征中，找哪些是和幸存相關 import numpy as np import matplotlib.pyplot as plt Pclass_Survied = pd.crosstab(df_train['Pclass'],df_train['Survived'])#生成Pclass_Survied的列聯表 In?[7]: Pclass_Survied Out[7]: Survived01Pclass??123

80	136
97	87
372	119

In?[8]: Pclass_Survied.plot(kind = 'bar',stacked = True) #堆積柱形圖 plt.show() In?[9]: Pclass_Survied.count() Out[9]: Survived 0 3 1 3 dtype: int64 In?[10]: Pclass_Survied.index Out[10]: Int64Index([1, 2, 3], dtype='int64', name='Pclass') In?[11]: Survied_len = len(Pclass_Survied.count()) Pclass_index = np.arange(len(Pclass_Survied.index)) In?[12]: Pclass_index Out[12]: array([0, 1, 2]) In?[13]: Pclass_Survied Out[13]: Survived01Pclass??123

80	136
97	87
372	119

In?[14]: Pclass_Survied.plot(kind = 'bar',stacked = True) #堆積柱形圖 Sum1 = 0 for i in range(Survied_len): SurvivedName = Pclass_Survied.columns[i] PclassCount = Pclass_Survied[SurvivedName] Sum1,Sum2 = Sum1+PclassCount,Sum1 Zsum =Sum2+(Sum1 - Sum2)/2 for x,y,z in zip(Pclass_index,PclassCount,Zsum): plt.text(x,z, '%.0f'%y, ha = 'center',va='center' )#添加數據標簽 #修改x軸標簽 plt.xticks(Pclass_Survied.index-1, Pclass_Survied.index, rotation=360) plt.title('Survived status by pclass') plt.show() In?[15]: a = df_train.Pclass[df_train['Survived']==0].value_counts() b = df_train.Pclass[df_train['Survived']==1].value_counts() Pclass_Survived = pd.DataFrame({ 0: a, 1: b}) In?[16]: Pclass_Survived Out[16]: ?01123

80	136
97	87
372	119

In?[17]: import re df_train['Appellation'] = df_train.Name.apply(lambda x: re.search('\w+\.', x).group()).str.replace('.', '') df_train.Appellation.unique() Out[17]: array(['Mr', 'Mrs', 'Miss', 'Master', 'Don', 'Rev', 'Dr', 'Mme', 'Ms','Major', 'Lady', 'Sir', 'Mlle', 'Col', 'Capt', 'Countess','Jonkheer'], dtype=object) In?[18]: Application_Sex = pd.crosstab(df_train.Sex,df_train.Appellation) Application_Sex Out[18]: AppellationCaptColCountessDonDrJonkheerLadyMajorMasterMissMlleMmeMrMrsMsRevSirSex?????????????????femalemale

0	0	1	0	1	0	1	0	0	182	2	1	0	125	1	0	0
1	2	0	1	6	1	0	2	40	0	0	0	517	0	0	6	1

In?[19]: df_train['Appellation'] = df_train['Appellation'].replace(['Capt','Col','Countess','Don','Dr','Jonkheer','Lady','Major','Rev','Sir'], 'Rare') df_train['Appellation'] = df_train['Appellation'].replace(['Mlle','Ms'], 'Miss') df_train['Appellation'] = df_train['Appellation'].replace('Mme', 'Mrs') df_train.Appellation.unique() Out[19]: array(['Mr', 'Mrs', 'Miss', 'Master', 'Rare'], dtype=object) In?[44]: Appellation_Survived = pd.crosstab(df_train['Appellation'], df_train['Survived']) Appellation_Survived.plot(kind = 'bar') plt.xticks(np.arange(len(Appellation_Survived.index)), Appellation_Survived.index, rotation = 360) plt.title('Survived status by Appellation') plt.show() In?[24]: Sex_Survived = pd.crosstab(df_train['Sex'],df_train['Survived']) In?[45]: #生成列聯表 Sex_Survived = pd.crosstab(df_train['Sex'], df_train['Survived']) Survived_len = len(Sex_Survived.count()) Sex_index = np.arange(len(Sex_Survived.index)) single_width = 0.35 for i in range(Survived_len): SurvivedName = Sex_Survived.columns[i] SexCount = Sex_Survived[SurvivedName] SexLocation = Sex_index * 1.05 + (i - 1/2)*single_width #繪制柱形圖 plt.bar(SexLocation, SexCount, width = single_width) for x, y in zip(SexLocation, SexCount): #添加數據標簽 plt.text(x, y, '%.0f'%y, ha='center', va='bottom') index = Sex_index * 1.05 plt.xticks(index, Sex_Survived.index, rotation=360) plt.title('Survived status by sex') plt.show() In?[46]: SibSp_Survived = pd.crosstab(df_train['SibSp'], df_train['Survived']) SibSp_Survived.plot(kind = 'bar') plt.xticks(SibSp_Survived.index,SibSp_Survived.index,rotation = 360) plt.title('Survived status by SibSp') plt.show() In?[47]: SibSp_Survived = pd.crosstab(df_train.SibSp[df_train['SibSp']>2], df_train['Survived']) SibSp_Survived.plot(kind = 'bar') plt.xticks([0,1,2,3],SibSp_Survived.index,rotation = 360) plt.title('Survived status by SibSp') plt.show() In?[28]: Ticket_Count = df_train.groupby('Ticket',as_index=False)['PassengerId'].count() In?[29]: Ticket_Count.head() Out[29]: ?TicketPassengerId01234

110152	3
110413	3
110465	2
110564	1
110813	1

In?[30]: #解釋上行代碼中的groupg中的as_index=False df = pd.DataFrame(data={'books':['bk1','bk1','bk1','bk2','bk2','bk3'], 'price': [12,12,12,15,15,17]}) print(df) print("*********************") print (df.groupby('books', as_index=True).sum()) print("*********************") print (df.groupby('books', as_index=False).sum()) books price 0 bk1 12 1 bk1 12 2 bk1 12 3 bk2 15 4 bk2 15 5 bk3 17 *********************price books bk1 36 bk2 30 bk3 17 *********************books price 0 bk1 36 1 bk2 30 2 bk3 17 In?[31]: Ticket_Count_0 = Ticket_Count[Ticket_Count.PassengerId == 1]['Ticket'] In?[32]: Ticket_Count_0.head() Out[32]: 3 110564 4 110813 5 111240 6 111320 8 111369 Name: Ticket, dtype: object In?[33]: df_train['GroupTicket'] = np.where(df_train.Ticket.isin(Ticket_Count_0),0,1) In?[34]: GroupTicket_Survived = pd.crosstab(df_train['GroupTicket'],df_train['Survived']) GroupTicket_Survived.plot(kind='bar') plt.xticks(rotation =360) Out[34]: (array([0, 1]), <a list of 2 Text xticklabel objects>) In?[35]: bins = [0, 60, 120, 180, 240, 300, 360, 420, 480, 540, 600] df_train['GroupFare'] = pd.cut(df_train.Fare,bins,right=False) GroupFare_Survived = pd.crosstab(df_train['GroupFare'],df_train['Survived']) GroupFare_Survived.plot(kind = 'bar') Out[35]: <matplotlib.axes._subplots.AxesSubplot at 0xac47eb8> In?[36]: GroupFare_Survived.iloc[2:].plot(kind = 'bar') Out[36]: <matplotlib.axes._subplots.AxesSubplot at 0xa7a4ef0> In?[?]: #以上所有操作都是對特征中無缺失部分進行分析 #下一步則會在特征工程中對缺失部分進行處理Age、Cabin、Embarked In?[37]: df_train['Embarked'].mode() Out[37]: 0 S dtype: object In?[38]: #df_train['Embarked'].mode()[0] 眾數可能有多個，[0]代表取第一個 train = df_train.copy() train['Embarked'] = train['Embarked'].fillna(train['Embarked'].mode()[0]) In?[39]: train['Cabin'] = train['Cabin'].fillna('NO') In?[40]: Age_Appellation_median = train.groupby('Appellation')['Age'].median() In?[52]: Age_Appellation_median Out[52]: Appellation Master 3.5 Miss 21.0 Mr 30.0 Mrs 35.0 Rare 48.5 Name: Age, dtype: float64 In?[59]: train.set_index('Appellation', inplace = True) #在當前表填充缺失值 train.Age.fillna(Age_Appellation_median, inplace = True) #重置索引 train.reset_index(inplace = True) In?[60]: train Out[60]: ?AppellationPassengerIdSurvivedPclassNameSexAgeSibSpParchTicketFareCabinEmbarkedGroupTicketGroupFare01234567891011121314151617181920212223242526272829...861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890

Mr	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NO	S	0	[0, 60)
Mrs	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C	0	[60, 120)
Miss	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NO	S	0	[0, 60)
Mrs	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S	1	[0, 60)
Mr	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NO	S	0	[0, 60)
Mr	6	0	3	Moran, Mr. James	male	30.0	0	0	330877	8.4583	NO	Q	0	[0, 60)
Mr	7	0	1	McCarthy, Mr. Timothy J	male	54.0	0	0	17463	51.8625	E46	S	0	[0, 60)
Master	8	0	3	Palsson, Master. Gosta Leonard	male	2.0	3	1	349909	21.0750	NO	S	1	[0, 60)
Mrs	9	1	3	Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)	female	27.0	0	2	347742	11.1333	NO	S	1	[0, 60)
Mrs	10	1	2	Nasser, Mrs. Nicholas (Adele Achem)	female	14.0	1	0	237736	30.0708	NO	C	1	[0, 60)
Miss	11	1	3	Sandstrom, Miss. Marguerite Rut	female	4.0	1	1	PP 9549	16.7000	G6	S	1	[0, 60)
Miss	12	1	1	Bonnell, Miss. Elizabeth	female	58.0	0	0	113783	26.5500	C103	S	0	[0, 60)
Mr	13	0	3	Saundercock, Mr. William Henry	male	20.0	0	0	A/5. 2151	8.0500	NO	S	0	[0, 60)
Mr	14	0	3	Andersson, Mr. Anders Johan	male	39.0	1	5	347082	31.2750	NO	S	1	[0, 60)
Miss	15	0	3	Vestrom, Miss. Hulda Amanda Adolfina	female	14.0	0	0	350406	7.8542	NO	S	0	[0, 60)
Mrs	16	1	2	Hewlett, Mrs. (Mary D Kingcome)	female	55.0	0	0	248706	16.0000	NO	S	0	[0, 60)
Master	17	0	3	Rice, Master. Eugene	male	2.0	4	1	382652	29.1250	NO	Q	1	[0, 60)
Mr	18	1	2	Williams, Mr. Charles Eugene	male	30.0	0	0	244373	13.0000	NO	S	0	[0, 60)
Mrs	19	0	3	Vander Planke, Mrs. Julius (Emelia Maria Vande...	female	31.0	1	0	345763	18.0000	NO	S	0	[0, 60)
Mrs	20	1	3	Masselmani, Mrs. Fatima	female	35.0	0	0	2649	7.2250	NO	C	0	[0, 60)
Mr	21	0	2	Fynney, Mr. Joseph J	male	35.0	0	0	239865	26.0000	NO	S	1	[0, 60)
Mr	22	1	2	Beesley, Mr. Lawrence	male	34.0	0	0	248698	13.0000	D56	S	0	[0, 60)
Miss	23	1	3	McGowan, Miss. Anna "Annie"	female	15.0	0	0	330923	8.0292	NO	Q	0	[0, 60)
Mr	24	1	1	Sloper, Mr. William Thompson	male	28.0	0	0	113788	35.5000	A6	S	0	[0, 60)
Miss	25	0	3	Palsson, Miss. Torborg Danira	female	8.0	3	1	349909	21.0750	NO	S	1	[0, 60)
Mrs	26	1	3	Asplund, Mrs. Carl Oscar (Selma Augusta Emilia...	female	38.0	1	5	347077	31.3875	NO	S	1	[0, 60)
Mr	27	0	3	Emir, Mr. Farred Chehab	male	30.0	0	0	2631	7.2250	NO	C	0	[0, 60)
Mr	28	0	1	Fortune, Mr. Charles Alexander	male	19.0	3	2	19950	263.0000	C23 C25 C27	S	1	[240, 300)
Miss	29	1	3	O'Dwyer, Miss. Ellen "Nellie"	female	21.0	0	0	330959	7.8792	NO	Q	0	[0, 60)
Mr	30	0	3	Todoroff, Mr. Lalio	male	30.0	0	0	349216	7.8958	NO	S	0	[0, 60)
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
Mr	862	0	2	Giles, Mr. Frederick Edward	male	21.0	1	0	28134	11.5000	NO	S	0	[0, 60)
Mrs	863	1	1	Swift, Mrs. Frederick Joel (Margaret Welles Ba...	female	48.0	0	0	17466	25.9292	D17	S	0	[0, 60)
Miss	864	0	3	Sage, Miss. Dorothy Edith "Dolly"	female	21.0	8	2	CA. 2343	69.5500	NO	S	1	[60, 120)
Mr	865	0	2	Gill, Mr. John William	male	24.0	0	0	233866	13.0000	NO	S	0	[0, 60)
Mrs	866	1	2	Bystrom, Mrs. (Karolina)	female	42.0	0	0	236852	13.0000	NO	S	0	[0, 60)
Miss	867	1	2	Duran y More, Miss. Asuncion	female	27.0	1	0	SC/PARIS 2149	13.8583	NO	C	0	[0, 60)
Mr	868	0	1	Roebling, Mr. Washington Augustus II	male	31.0	0	0	PC 17590	50.4958	A24	S	0	[0, 60)
Mr	869	0	3	van Melkebeke, Mr. Philemon	male	30.0	0	0	345777	9.5000	NO	S	0	[0, 60)
Master	870	1	3	Johnson, Master. Harold Theodor	male	4.0	1	1	347742	11.1333	NO	S	1	[0, 60)
Mr	871	0	3	Balkic, Mr. Cerin	male	26.0	0	0	349248	7.8958	NO	S	0	[0, 60)
Mrs	872	1	1	Beckwith, Mrs. Richard Leonard (Sallie Monypeny)	female	47.0	1	1	11751	52.5542	D35	S	1	[0, 60)
Mr	873	0	1	Carlsson, Mr. Frans Olof	male	33.0	0	0	695	5.0000	B51 B53 B55	S	0	[0, 60)
Mr	874	0	3	Vander Cruyssen, Mr. Victor	male	47.0	0	0	345765	9.0000	NO	S	0	[0, 60)
Mrs	875	1	2	Abelson, Mrs. Samuel (Hannah Wizosky)	female	28.0	1	0	P/PP 3381	24.0000	NO	C	1	[0, 60)
Miss	876	1	3	Najib, Miss. Adele Kiamie "Jane"	female	15.0	0	0	2667	7.2250	NO	C	0	[0, 60)
Mr	877	0	3	Gustafsson, Mr. Alfred Ossian	male	20.0	0	0	7534	9.8458	NO	S	1	[0, 60)
Mr	878	0	3	Petroff, Mr. Nedelio	male	19.0	0	0	349212	7.8958	NO	S	0	[0, 60)
Mr	879	0	3	Laleff, Mr. Kristo	male	30.0	0	0	349217	7.8958	NO	S	0	[0, 60)
Mrs	880	1	1	Potter, Mrs. Thomas Jr (Lily Alexenia Wilson)	female	56.0	0	1	11767	83.1583	C50	C	1	[60, 120)
Mrs	881	1	2	Shelley, Mrs. William (Imanita Parrish Hall)	female	25.0	0	1	230433	26.0000	NO	S	1	[0, 60)
Mr	882	0	3	Markun, Mr. Johann	male	33.0	0	0	349257	7.8958	NO	S	0	[0, 60)
Miss	883	0	3	Dahlberg, Miss. Gerda Ulrika	female	22.0	0	0	7552	10.5167	NO	S	0	[0, 60)
Mr	884	0	2	Banfield, Mr. Frederick James	male	28.0	0	0	C.A./SOTON 34068	10.5000	NO	S	0	[0, 60)
Mr	885	0	3	Sutehall, Mr. Henry Jr	male	25.0	0	0	SOTON/OQ 392076	7.0500	NO	S	0	[0, 60)
Mrs	886	0	3	Rice, Mrs. William (Margaret Norton)	female	39.0	0	5	382652	29.1250	NO	Q	1	[0, 60)
Rare	887	0	2	Montvila, Rev. Juozas	male	27.0	0	0	211536	13.0000	NO	S	0	[0, 60)
Miss	888	1	1	Graham, Miss. Margaret Edith	female	19.0	0	0	112053	30.0000	B42	S	0	[0, 60)
Miss	889	0	3	Johnston, Miss. Catherine Helen "Carrie"	female	21.0	1	2	W./C. 6607	23.4500	NO	S	1	[0, 60)
Mr	890	1	1	Behr, Mr. Karl Howell	male	26.0	0	0	111369	30.0000	C148	C	0	[0, 60)
Mr	891	0	3	Dooley, Mr. Patrick	male	32.0	0	0	370376	7.7500	NO	Q	0	[0, 60)

891 rows × 15 columns

In?[62]: train.Age.isnull().sum() Out[62]: 0 In?[64]: train.Age.isnull().any() Out[64]: False In?[65]: train.Age.describe() Out[65]: count 891.000000 mean 29.392447 std 13.268389 min 0.420000 25% 21.000000 50% 30.000000 75% 35.000000 max 80.000000 Name: Age, dtype: float64 In?[66]: Embarked_Survived = pd.crosstab(train['Embarked'],train['Survived']) In?[68]: Embarked_Survived.plot(kind = 'bar') plt.xticks(rotation = 360) plt.title('Survived status by Embarked') plt.show() In?[69]: train Out[69]: ?AppellationPassengerIdSurvivedPclassNameSexAgeSibSpParchTicketFareCabinEmbarkedGroupTicketGroupFare01234567891011121314151617181920212223242526272829...861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890

Mr	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NO	S	0	[0, 60)
Mrs	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C	0	[60, 120)
Miss	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NO	S	0	[0, 60)
Mrs	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S	1	[0, 60)
Mr	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NO	S	0	[0, 60)
Mr	6	0	3	Moran, Mr. James	male	30.0	0	0	330877	8.4583	NO	Q	0	[0, 60)
Mr	7	0	1	McCarthy, Mr. Timothy J	male	54.0	0	0	17463	51.8625	E46	S	0	[0, 60)
Master	8	0	3	Palsson, Master. Gosta Leonard	male	2.0	3	1	349909	21.0750	NO	S	1	[0, 60)
Mrs	9	1	3	Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)	female	27.0	0	2	347742	11.1333	NO	S	1	[0, 60)
Mrs	10	1	2	Nasser, Mrs. Nicholas (Adele Achem)	female	14.0	1	0	237736	30.0708	NO	C	1	[0, 60)
Miss	11	1	3	Sandstrom, Miss. Marguerite Rut	female	4.0	1	1	PP 9549	16.7000	G6	S	1	[0, 60)
Miss	12	1	1	Bonnell, Miss. Elizabeth	female	58.0	0	0	113783	26.5500	C103	S	0	[0, 60)
Mr	13	0	3	Saundercock, Mr. William Henry	male	20.0	0	0	A/5. 2151	8.0500	NO	S	0	[0, 60)
Mr	14	0	3	Andersson, Mr. Anders Johan	male	39.0	1	5	347082	31.2750	NO	S	1	[0, 60)
Miss	15	0	3	Vestrom, Miss. Hulda Amanda Adolfina	female	14.0	0	0	350406	7.8542	NO	S	0	[0, 60)
Mrs	16	1	2	Hewlett, Mrs. (Mary D Kingcome)	female	55.0	0	0	248706	16.0000	NO	S	0	[0, 60)
Master	17	0	3	Rice, Master. Eugene	male	2.0	4	1	382652	29.1250	NO	Q	1	[0, 60)
Mr	18	1	2	Williams, Mr. Charles Eugene	male	30.0	0	0	244373	13.0000	NO	S	0	[0, 60)
Mrs	19	0	3	Vander Planke, Mrs. Julius (Emelia Maria Vande...	female	31.0	1	0	345763	18.0000	NO	S	0	[0, 60)
Mrs	20	1	3	Masselmani, Mrs. Fatima	female	35.0	0	0	2649	7.2250	NO	C	0	[0, 60)
Mr	21	0	2	Fynney, Mr. Joseph J	male	35.0	0	0	239865	26.0000	NO	S	1	[0, 60)
Mr	22	1	2	Beesley, Mr. Lawrence	male	34.0	0	0	248698	13.0000	D56	S	0	[0, 60)
Miss	23	1	3	McGowan, Miss. Anna "Annie"	female	15.0	0	0	330923	8.0292	NO	Q	0	[0, 60)
Mr	24	1	1	Sloper, Mr. William Thompson	male	28.0	0	0	113788	35.5000	A6	S	0	[0, 60)
Miss	25	0	3	Palsson, Miss. Torborg Danira	female	8.0	3	1	349909	21.0750	NO	S	1	[0, 60)
Mrs	26	1	3	Asplund, Mrs. Carl Oscar (Selma Augusta Emilia...	female	38.0	1	5	347077	31.3875	NO	S	1	[0, 60)
Mr	27	0	3	Emir, Mr. Farred Chehab	male	30.0	0	0	2631	7.2250	NO	C	0	[0, 60)
Mr	28	0	1	Fortune, Mr. Charles Alexander	male	19.0	3	2	19950	263.0000	C23 C25 C27	S	1	[240, 300)
Miss	29	1	3	O'Dwyer, Miss. Ellen "Nellie"	female	21.0	0	0	330959	7.8792	NO	Q	0	[0, 60)
Mr	30	0	3	Todoroff, Mr. Lalio	male	30.0	0	0	349216	7.8958	NO	S	0	[0, 60)
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
Mr	862	0	2	Giles, Mr. Frederick Edward	male	21.0	1	0	28134	11.5000	NO	S	0	[0, 60)
Mrs	863	1	1	Swift, Mrs. Frederick Joel (Margaret Welles Ba...	female	48.0	0	0	17466	25.9292	D17	S	0	[0, 60)
Miss	864	0	3	Sage, Miss. Dorothy Edith "Dolly"	female	21.0	8	2	CA. 2343	69.5500	NO	S	1	[60, 120)
Mr	865	0	2	Gill, Mr. John William	male	24.0	0	0	233866	13.0000	NO	S	0	[0, 60)
Mrs	866	1	2	Bystrom, Mrs. (Karolina)	female	42.0	0	0	236852	13.0000	NO	S	0	[0, 60)
Miss	867	1	2	Duran y More, Miss. Asuncion	female	27.0	1	0	SC/PARIS 2149	13.8583	NO	C	0	[0, 60)
Mr	868	0	1	Roebling, Mr. Washington Augustus II	male	31.0	0	0	PC 17590	50.4958	A24	S	0	[0, 60)
Mr	869	0	3	van Melkebeke, Mr. Philemon	male	30.0	0	0	345777	9.5000	NO	S	0	[0, 60)
Master	870	1	3	Johnson, Master. Harold Theodor	male	4.0	1	1	347742	11.1333	NO	S	1	[0, 60)
Mr	871	0	3	Balkic, Mr. Cerin	male	26.0	0	0	349248	7.8958	NO	S	0	[0, 60)
Mrs	872	1	1	Beckwith, Mrs. Richard Leonard (Sallie Monypeny)	female	47.0	1	1	11751	52.5542	D35	S	1	[0, 60)
Mr	873	0	1	Carlsson, Mr. Frans Olof	male	33.0	0	0	695	5.0000	B51 B53 B55	S	0	[0, 60)
Mr	874	0	3	Vander Cruyssen, Mr. Victor	male	47.0	0	0	345765	9.0000	NO	S	0	[0, 60)
Mrs	875	1	2	Abelson, Mrs. Samuel (Hannah Wizosky)	female	28.0	1	0	P/PP 3381	24.0000	NO	C	1	[0, 60)
Miss	876	1	3	Najib, Miss. Adele Kiamie "Jane"	female	15.0	0	0	2667	7.2250	NO	C	0	[0, 60)
Mr	877	0	3	Gustafsson, Mr. Alfred Ossian	male	20.0	0	0	7534	9.8458	NO	S	1	[0, 60)
Mr	878	0	3	Petroff, Mr. Nedelio	male	19.0	0	0	349212	7.8958	NO	S	0	[0, 60)
Mr	879	0	3	Laleff, Mr. Kristo	male	30.0	0	0	349217	7.8958	NO	S	0	[0, 60)
Mrs	880	1	1	Potter, Mrs. Thomas Jr (Lily Alexenia Wilson)	female	56.0	0	1	11767	83.1583	C50	C	1	[60, 120)
Mrs	881	1	2	Shelley, Mrs. William (Imanita Parrish Hall)	female	25.0	0	1	230433	26.0000	NO	S	1	[0, 60)
Mr	882	0	3	Markun, Mr. Johann	male	33.0	0	0	349257	7.8958	NO	S	0	[0, 60)
Miss	883	0	3	Dahlberg, Miss. Gerda Ulrika	female	22.0	0	0	7552	10.5167	NO	S	0	[0, 60)
Mr	884	0	2	Banfield, Mr. Frederick James	male	28.0	0	0	C.A./SOTON 34068	10.5000	NO	S	0	[0, 60)
Mr	885	0	3	Sutehall, Mr. Henry Jr	male	25.0	0	0	SOTON/OQ 392076	7.0500	NO	S	0	[0, 60)
Mrs	886	0	3	Rice, Mrs. William (Margaret Norton)	female	39.0	0	5	382652	29.1250	NO	Q	1	[0, 60)
Rare	887	0	2	Montvila, Rev. Juozas	male	27.0	0	0	211536	13.0000	NO	S	0	[0, 60)
Miss	888	1	1	Graham, Miss. Margaret Edith	female	19.0	0	0	112053	30.0000	B42	S	0	[0, 60)
Miss	889	0	3	Johnston, Miss. Catherine Helen "Carrie"	female	21.0	1	2	W./C. 6607	23.4500	NO	S	1	[0, 60)
Mr	890	1	1	Behr, Mr. Karl Howell	male	26.0	0	0	111369	30.0000	C148	C	0	[0, 60)
Mr	891	0	3	Dooley, Mr. Patrick	male	32.0	0	0	370376	7.7500	NO	Q	0	[0, 60)

891 rows × 15 columns

In?[80]: train['GroupCabin'] = np.where(train['Cabin'] == 'NO',0,1) In?[82]: GroupCabin_Survived = pd.crosstab(train['GroupCabin'],train['Survived']) GroupCabin_Survived.plot(kind = 'bar') plt.title('Survived status by GroupCabin') plt.xticks(rotation=360) plt.show() In?[86]: #對Age進行分組: 2**10>891分成10組, 組距為(最大值80-最小值0)/10 =8取9 bins = [0, 9, 18, 27, 36, 45, 54, 63, 72, 81, 90] train['GroupAge'] = pd.cut(train.Age, bins) GroupAge_Survived = pd.crosstab(train['GroupAge'], train['Survived']) GroupAge_Survived.plot(kind = 'bar') plt.title('Survived status by GroupAge') plt.show() In?[87]: train['Appellation'] = train.Appellation.map({'Mr': 0, 'Mrs': 1, 'Miss': 2, 'Master': 3, 'Rare': 4}) train.Appellation.unique() Out[87]: array([0, 1, 2, 3, 4], dtype=int64) In?[89]: train['Sex'] = train.Sex.map({'female':0,'male':1}) In?[90]: train.head() Out[90]: ?AppellationPassengerIdSurvivedPclassNameSexAgeSibSpParchTicketFareCabinEmbarkedGroupTicketGroupFareGroupCabinGroupAge01234

0	1	0	3	Braund, Mr. Owen Harris	1	22.0	1	A/5 21171	7.2500	NO	S	0	[0, 60)	0	(18, 27]
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	0	38.0	1	PC 17599	71.2833	C85	C	0	[60, 120)	1	(36, 45]
2	3	1	3	Heikkinen, Miss. Laina	0	26.0	0	STON/O2. 3101282	7.9250	NO	S	0	[0, 60)	0	(18, 27]
1	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	0	35.0	1	113803	53.1000	C123	S	1	[0, 60)	1	(27, 36]
0	5	0	3	Allen, Mr. William Henry	1	35.0	0	373450	8.0500	NO	S	0	[0, 60)	0	(27, 36]

In?[95]: train.loc[train['Age'] < 9, 'Age']=0 train.loc[(train['Age'] >= 9) & (train['Age'] < 18), 'Age'] = 1 train.loc[(train['Age'] >= 18) & (train['Age'] < 27), 'Age'] = 2 train.loc[(train['Age'] >= 27) & (train['Age'] < 36), 'Age'] = 3 train.loc[(train['Age'] >= 36) & (train['Age'] < 45), 'Age'] = 4 train.loc[(train['Age'] >= 45) & (train['Age'] < 54), 'Age'] = 5 train.loc[(train['Age'] >= 54) & (train['Age'] < 63), 'Age'] = 6 train.loc[(train['Age'] >= 63) & (train['Age'] < 72), 'Age'] = 7 train.loc[(train['Age'] >= 72) & (train['Age'] < 81), 'Age'] = 8 train.loc[(train['Age'] >= 81) & (train['Age'] < 90), 'Age'] = 9 train.Age.unique() Out[95]: array([ 2., 4., 3., 6., 0., 1., 7., 5., 8.]) In?[96]: train.head() Out[96]: ?AppellationPassengerIdSurvivedPclassNameSexAgeSibSpParchTicketFareCabinEmbarkedGroupTicketGroupFareGroupCabinGroupAge01234

0	1	0	3	Braund, Mr. Owen Harris	1	2.0	1	A/5 21171	7.2500	NO	S	0	[0, 60)	0	(18, 27]
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	0	4.0	1	PC 17599	71.2833	C85	C	0	[60, 120)	1	(36, 45]
2	3	1	3	Heikkinen, Miss. Laina	0	2.0	0	STON/O2. 3101282	7.9250	NO	S	0	[0, 60)	0	(18, 27]
1	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	0	3.0	1	113803	53.1000	C123	S	1	[0, 60)	1	(27, 36]
0	5	0	3	Allen, Mr. William Henry	1	3.0	0	373450	8.0500	NO	S	0	[0, 60)	0	(27, 36]

In?[97]: #當SibSp和Parch都為0時, 則孤身一人. train['FamilySize'] = train['SibSp'] + train['Parch'] + 1 train.FamilySize.unique() Out[97]: array([ 2, 1, 5, 3, 7, 6, 4, 8, 11], dtype=int64) In?[98]: train.loc[train['Fare'] < 60, 'Fare'] = 0 train.loc[(train['Fare'] >= 60) & (train['Fare'] < 120), 'Fare'] = 1 train.loc[(train['Fare'] >= 120) & (train['Fare'] < 180), 'Fare'] = 2 train.loc[(train['Fare'] >= 180) & (train['Fare'] < 240), 'Fare'] = 3 train.loc[(train['Fare'] >= 240) & (train['Fare'] < 300), 'Fare'] = 4 train.loc[(train['Fare'] >= 300) & (train['Fare'] < 360), 'Fare'] = 5 train.loc[(train['Fare'] >= 360) & (train['Fare'] < 420), 'Fare'] = 6 train.loc[(train['Fare'] >= 420) & (train['Fare'] < 480), 'Fare'] = 7 train.loc[(train['Fare'] >= 480) & (train['Fare'] < 540), 'Fare'] = 8 train.loc[(train['Fare'] >= 540) & (train['Fare'] < 600), 'Fare'] = 9 train.Fare.unique() Out[98]: array([ 0., 1., 4., 2., 8., 3.]) In?[99]: train['Embarked'] = train.Embarked.map({'S': 0, 'C': 1, 'Q': 2}) In?[100]: train.drop(['PassengerId', 'Name', 'GroupAge', 'SibSp', 'Parch', 'Ticket', 'GroupFare', 'Cabin'], axis = 1, inplace =True) In?[110]: from sklearn.linear_model import LogisticRegression from sklearn.model_selection import train_test_split X=train[['Pclass', 'Appellation', 'Sex', 'Age', 'FamilySize', 'GroupTicket', 'Fare', 'GroupCabin', 'Embarked']] y=train['Survived'] #隨機劃分訓練集和測試集 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2) #邏輯回歸模型初始化 lg = LogisticRegression() #訓練邏輯回歸模型 lg.fit(X_train, y_train) #用測試數據檢驗模型好壞 lg.score(X_test, y_test) Out[110]: 0.78212290502793291 In?[111]: from sklearn.tree import DecisionTreeClassifier #樹的最大深度為15, 內部節點再劃分所需最小樣本數為2, 葉節點最小樣本數1, 最大葉子節點數10, 每次分類的最大特征數6 dt = DecisionTreeClassifier(max_depth=15, min_samples_split=2, min_samples_leaf=1, max_leaf_nodes=10, max_features=6) dt.fit(X_train, y_train) dt.score(X_test, y_test) Out[111]: 0.79329608938547491 In?[126]: #支持向量機SVM from sklearn.cross_validation import cross_val_score, KFold from scipy.stats import sem # 構造一個便于交叉驗證模型性能的函數（模塊） def evaluate_cross_validation(clf, X, y, K): # KFold 函數需要如下參數：數據量, 叉驗次數, 是否洗牌 cv = KFold(len(y), K, shuffle=True, random_state = 0) # 采用上述的分隔方式進行交叉驗證，測試模型性能，對于分類問題，這些得分默認是accuracy，也可以修改為別的 scores = cross_val_score(clf, X, y, cv=cv) print (scores) print ('Mean score: %.3f (+/-%.3f)' % (scores.mean(), sem(scores))) # 使用線性核的SVC （后面會說到不同的核，結果可能大不相同） svc_linear = SVC(kernel='rbf')#‘linear’:線性核函數‘poly’：多項式核函數‘rbf’：徑像核函數/高斯核‘sigmod’:sigmod核函數‘precomputed’:核矩陣 # 五折交叉驗證 K = 5 evaluate_cross_validation(svc_linear, X_train, y_train, 5) [ 0.82517483 0.86013986 0.80985915 0.83802817 0.87323944] Mean score: 0.841 (+/-0.011) In?[118]: #線性分類器 from sklearn.linear_model import SGDClassifier # 選擇使用SGD分類器，適合大規模數據，隨機梯度下降方法估計參數 clf = SGDClassifier() clf.fit(X_train, y_train) # 導入評價包 from sklearn import metrics y_train_predict = clf.predict(X_train) # 內測，使用訓練樣本進行準確性能評估 print(metrics.accuracy_score(y_train, y_train_predict)) # 標準外測，使用測試樣本進行準確性能評估 y_predict = clf.predict(X_test) print(metrics.accuracy_score(y_test, y_predict)) 0.651685393258 0.659217877095 In?[123]: #樸素貝葉斯分類器 from sklearn.naive_bayes import GaussianNB clf = GaussianNB() clf.fit(X_train, y_train) y_predict =clf.predict(X_test) from sklearn.metrics import accuracy_score print(accuracy_score(y_test, y_predict)) 0.765363128492

轉載于:https://www.cnblogs.com/USTC-ZCC/p/10018777.html

總結

以上是生活随笔為你收集整理的泰坦尼克号项目的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。

上一篇：全方位了解平台爆款，解析B站热销商品，实
下一篇：字符串(づ｡◕‿‿◕｡)づ进阶之章