파이썬_Titanic 생존여부 예측

In [2]:

pip install plotly

Requirement already satisfied: plotly in c:\users\flyto\anaconda3\lib\site-packages (4.9.0)
Requirement already satisfied: six in c:\users\flyto\anaconda3\lib\site-packages (from plotly) (1.15.0)
Requirement already satisfied: retrying>=1.3.3 in c:\users\flyto\anaconda3\lib\site-packages (from plotly) (1.3.3)
Note: you may need to restart the kernel to use updated packages.

In [3]:

pip install cufflinks

Requirement already satisfied: cufflinks in c:\users\flyto\anaconda3\lib\site-packages (0.17.3)
Requirement already satisfied: ipython>=5.3.0 in c:\users\flyto\anaconda3\lib\site-packages (from cufflinks) (7.16.1)
Requirement already satisfied: colorlover>=0.2.1 in c:\users\flyto\anaconda3\lib\site-packages (from cufflinks) (0.3.0)
Requirement already satisfied: numpy>=1.9.2 in c:\users\flyto\anaconda3\lib\site-packages (from cufflinks) (1.18.5)
Requirement already satisfied: six>=1.9.0 in c:\users\flyto\anaconda3\lib\site-packages (from cufflinks) (1.15.0)
Requirement already satisfied: setuptools>=34.4.1 in c:\users\flyto\anaconda3\lib\site-packages (from cufflinks) (49.2.0.post20200714)
Requirement already satisfied: ipywidgets>=7.0.0 in c:\users\flyto\anaconda3\lib\site-packages (from cufflinks) (7.5.1)
Requirement already satisfied: plotly>=4.1.1 in c:\users\flyto\anaconda3\lib\site-packages (from cufflinks) (4.9.0)
Requirement already satisfied: pandas>=0.19.2 in c:\users\flyto\anaconda3\lib\site-packages (from cufflinks) (1.0.5)
Requirement already satisfied: jedi>=0.10 in c:\users\flyto\anaconda3\lib\site-packages (from ipython>=5.3.0->cufflinks) (0.17.1)
Requirement already satisfied: decorator in c:\users\flyto\anaconda3\lib\site-packages (from ipython>=5.3.0->cufflinks) (4.4.2)
Requirement already satisfied: backcall in c:\users\flyto\anaconda3\lib\site-packages (from ipython>=5.3.0->cufflinks) (0.2.0)
Requirement already satisfied: pygments in c:\users\flyto\anaconda3\lib\site-packages (from ipython>=5.3.0->cufflinks) (2.6.1)
Requirement already satisfied: pickleshare in c:\users\flyto\anaconda3\lib\site-packages (from ipython>=5.3.0->cufflinks) (0.7.5)
Requirement already satisfied: prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0 in c:\users\flyto\anaconda3\lib\site-packages (from ipython>=5.3.0->cufflinks) (3.0.5)
Requirement already satisfied: colorama; sys_platform == "win32" in c:\users\flyto\anaconda3\lib\site-packages (from ipython>=5.3.0->cufflinks) (0.4.3)
Requirement already satisfied: traitlets>=4.2 in c:\users\flyto\anaconda3\lib\site-packages (from ipython>=5.3.0->cufflinks) (4.3.3)
Requirement already satisfied: ipykernel>=4.5.1 in c:\users\flyto\anaconda3\lib\site-packages (from ipywidgets>=7.0.0->cufflinks) (5.3.2)
Requirement already satisfied: widgetsnbextension~=3.5.0 in c:\users\flyto\anaconda3\lib\site-packages (from ipywidgets>=7.0.0->cufflinks) (3.5.1)
Requirement already satisfied: nbformat>=4.2.0 in c:\users\flyto\anaconda3\lib\site-packages (from ipywidgets>=7.0.0->cufflinks) (5.0.7)
Requirement already satisfied: retrying>=1.3.3 in c:\users\flyto\anaconda3\lib\site-packages (from plotly>=4.1.1->cufflinks) (1.3.3)
Requirement already satisfied: pytz>=2017.2 in c:\users\flyto\anaconda3\lib\site-packages (from pandas>=0.19.2->cufflinks) (2020.1)
Requirement already satisfied: python-dateutil>=2.6.1 in c:\users\flyto\anaconda3\lib\site-packages (from pandas>=0.19.2->cufflinks) (2.8.1)
Requirement already satisfied: parso<0.8.0,>=0.7.0 in c:\users\flyto\anaconda3\lib\site-packages (from jedi>=0.10->ipython>=5.3.0->cufflinks) (0.7.0)
Requirement already satisfied: wcwidth in c:\users\flyto\anaconda3\lib\site-packages (from prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0->ipython>=5.3.0->cufflinks) (0.2.5)
Requirement already satisfied: ipython-genutils in c:\users\flyto\anaconda3\lib\site-packages (from traitlets>=4.2->ipython>=5.3.0->cufflinks) (0.2.0)
Requirement already satisfied: tornado>=4.2 in c:\users\flyto\anaconda3\lib\site-packages (from ipykernel>=4.5.1->ipywidgets>=7.0.0->cufflinks) (6.0.4)
Requirement already satisfied: jupyter-client in c:\users\flyto\anaconda3\lib\site-packages (from ipykernel>=4.5.1->ipywidgets>=7.0.0->cufflinks) (6.1.6)
Requirement already satisfied: notebook>=4.4.1 in c:\users\flyto\anaconda3\lib\site-packages (from widgetsnbextension~=3.5.0->ipywidgets>=7.0.0->cufflinks) (6.0.3)
Requirement already satisfied: jupyter-core in c:\users\flyto\anaconda3\lib\site-packages (from nbformat>=4.2.0->ipywidgets>=7.0.0->cufflinks) (4.6.3)
Requirement already satisfied: jsonschema!=2.5.0,>=2.4 in c:\users\flyto\anaconda3\lib\site-packages (from nbformat>=4.2.0->ipywidgets>=7.0.0->cufflinks) (3.2.0)
Requirement already satisfied: pyzmq>=13 in c:\users\flyto\anaconda3\lib\site-packages (from jupyter-client->ipykernel>=4.5.1->ipywidgets>=7.0.0->cufflinks) (19.0.1)
Requirement already satisfied: prometheus-client in c:\users\flyto\anaconda3\lib\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets>=7.0.0->cufflinks) (0.8.0)
Requirement already satisfied: Send2Trash in c:\users\flyto\anaconda3\lib\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets>=7.0.0->cufflinks) (1.5.0)
Requirement already satisfied: jinja2 in c:\users\flyto\anaconda3\lib\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets>=7.0.0->cufflinks) (2.11.2)
Requirement already satisfied: nbconvert in c:\users\flyto\anaconda3\lib\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets>=7.0.0->cufflinks) (5.6.1)
Requirement already satisfied: terminado>=0.8.1 in c:\users\flyto\anaconda3\lib\site-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets>=7.0.0->cufflinks) (0.8.3)
Requirement already satisfied: pywin32>=1.0; sys_platform == "win32" in c:\users\flyto\anaconda3\lib\site-packages (from jupyter-core->nbformat>=4.2.0->ipywidgets>=7.0.0->cufflinks) (227)
Requirement already satisfied: attrs>=17.4.0 in c:\users\flyto\anaconda3\lib\site-packages (from jsonschema!=2.5.0,>=2.4->nbformat>=4.2.0->ipywidgets>=7.0.0->cufflinks) (19.3.0)
Requirement already satisfied: pyrsistent>=0.14.0 in c:\users\flyto\anaconda3\lib\site-packages (from jsonschema!=2.5.0,>=2.4->nbformat>=4.2.0->ipywidgets>=7.0.0->cufflinks) (0.16.0)
Requirement already satisfied: MarkupSafe>=0.23 in c:\users\flyto\anaconda3\lib\site-packages (from jinja2->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets>=7.0.0->cufflinks) (1.1.1)
Requirement already satisfied: bleach in c:\users\flyto\anaconda3\lib\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets>=7.0.0->cufflinks) (3.1.5)
Requirement already satisfied: defusedxml in c:\users\flyto\anaconda3\lib\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets>=7.0.0->cufflinks) (0.6.0)
Requirement already satisfied: mistune<2,>=0.8.1 in c:\users\flyto\anaconda3\lib\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets>=7.0.0->cufflinks) (0.8.4)
Requirement already satisfied: pandocfilters>=1.4.1 in c:\users\flyto\anaconda3\lib\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets>=7.0.0->cufflinks) (1.4.2)
Requirement already satisfied: testpath in c:\users\flyto\anaconda3\lib\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets>=7.0.0->cufflinks) (0.4.4)
Requirement already satisfied: entrypoints>=0.2.2 in c:\users\flyto\anaconda3\lib\site-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets>=7.0.0->cufflinks) (0.3)
Requirement already satisfied: webencodings in c:\users\flyto\anaconda3\lib\site-packages (from bleach->nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets>=7.0.0->cufflinks) (0.5.1)
Requirement already satisfied: packaging in c:\users\flyto\anaconda3\lib\site-packages (from bleach->nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets>=7.0.0->cufflinks) (20.4)
Requirement already satisfied: pyparsing>=2.0.2 in c:\users\flyto\anaconda3\lib\site-packages (from packaging->bleach->nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets>=7.0.0->cufflinks) (2.4.7)
Note: you may need to restart the kernel to use updated packages.

In [4]:

pip install chart_studio

Collecting chart_studio
  Downloading chart_studio-1.1.0-py3-none-any.whl (64 kB)
Requirement already satisfied: retrying>=1.3.3 in c:\users\flyto\anaconda3\lib\site-packages (from chart_studio) (1.3.3)
Requirement already satisfied: requests in c:\users\flyto\anaconda3\lib\site-packages (from chart_studio) (2.24.0)
Requirement already satisfied: plotly in c:\users\flyto\anaconda3\lib\site-packages (from chart_studio) (4.9.0)
Requirement already satisfied: six in c:\users\flyto\anaconda3\lib\site-packages (from chart_studio) (1.15.0)
Requirement already satisfied: certifi>=2017.4.17 in c:\users\flyto\anaconda3\lib\site-packages (from requests->chart_studio) (2020.6.20)
Requirement already satisfied: chardet<4,>=3.0.2 in c:\users\flyto\anaconda3\lib\site-packages (from requests->chart_studio) (3.0.4)
Requirement already satisfied: idna<3,>=2.5 in c:\users\flyto\anaconda3\lib\site-packages (from requests->chart_studio) (2.10)
Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in c:\users\flyto\anaconda3\lib\site-packages (from requests->chart_studio) (1.25.9)
Note: you may need to restart the kernel to use updated packages.
Installing collected packages: chart-studio
Successfully installed chart-studio-1.1.0

In [5]:

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import chart_studio.plotly as py
import cufflinks as cf
cf.go_offline(connected=True)

In [6]:

#train=pd.read_csv('D:\\me\\mine\\python\\titanic\\train.csv',dtype={'Pclass':str})
train=pd.read_csv('C:\\Users\\flyto\\Documents\\me\\kaggle\\titanic\\train.csv',dtype={'Pclass':str})

In [7]:

train.head()

Out[7]:

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

In [8]:

#test=pd.read_csv('D:\\me\\mine\\python\\titanic\\test.csv',dtype={'Pclass':str})
test=pd.read_csv('C:\\Users\\flyto\\Documents\\me\\kaggle\\titanic\\test.csv',dtype={'Pclass':str})

In [9]:

test.head()

Out[9]:

	PassengerId	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	892	3	Kelly, Mr. James	male	34.5	0	0	330911	7.8292	NaN	Q
1	893	3	Wilkes, Mrs. James (Ellen Needs)	female	47.0	1	0	363272	7.0000	NaN	S
2	894	2	Myles, Mr. Thomas Francis	male	62.0	0	0	240276	9.6875	NaN	Q
3	895	3	Wirz, Mr. Albert	male	27.0	0	0	315154	8.6625	NaN	S
4	896	3	Hirvonen, Mrs. Alexander (Helga E Lindqvist)	female	22.0	1	1	3101298	12.2875	NaN	S

In [10]:

train.isnull().sum()

Out[10]:

PassengerId      0
Survived         0
Pclass           0
Name             0
Sex              0
Age            177
SibSp            0
Parch            0
Ticket           0
Fare             0
Cabin          687
Embarked         2
dtype: int64

In [11]:

import seaborn as sns
sns.distplot(train['Age'],bins=20)
plt.show()

In [12]:

train.dtypes

Out[12]:

PassengerId      int64
Survived         int64
Pclass          object
Name            object
Sex             object
Age            float64
SibSp            int64
Parch            int64
Ticket          object
Fare           float64
Cabin           object
Embarked        object
dtype: object

In [13]:

train['Age']=train['Age'].fillna(train['Age'].mean())
train.isnull().sum()

Out[13]:

PassengerId      0
Survived         0
Pclass           0
Name             0
Sex              0
Age              0
SibSp            0
Parch            0
Ticket           0
Fare             0
Cabin          687
Embarked         2
dtype: int64

In [14]:

train['Age10']=(np.ceil(train['Age']/ 10) * 10).astype(int)
train.head()

Out[14]:

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked	Age10
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S	30
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C	40
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S	30
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S	40
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S	40

In [15]:

sns.distplot(train['Age10'],bins=10)
plt.show()

In [16]:

train.dtypes

Out[16]:

PassengerId      int64
Survived         int64
Pclass          object
Name            object
Sex             object
Age            float64
SibSp            int64
Parch            int64
Ticket          object
Fare           float64
Cabin           object
Embarked        object
Age10            int32
dtype: object

In [17]:

train['Cabin']

Out[17]:

0       NaN
1       C85
2       NaN
3      C123
4       NaN
       ... 
886     NaN
887     B42
888     NaN
889    C148
890     NaN
Name: Cabin, Length: 891, dtype: object

In [18]:

train.groupby('Cabin').sum()

Out[18]:

	PassengerId	Survived	Age	SibSp	Parch	Fare	Age10
Cabin
A10	584	0	36.000000	0	0	40.1250	40
A14	476	0	29.699118	0	0	52.0000	30
A16	557	1	48.000000	1	0	39.6000	50
A19	285	0	29.699118	0	0	26.0000	30
A20	600	1	49.000000	1	0	56.9292	50
...	...	...	...	...	...	...	...
F33	930	3	87.000000	0	0	34.0000	100
F38	777	0	29.699118	0	0	7.7500	30
F4	803	2	5.000000	4	2	78.0000	20
G6	864	2	59.000000	2	5	54.3250	80
T	340	0	45.000000	0	0	35.5000	50

147 rows × 7 columns

In [19]:

train.groupby('Cabin').mean()

Out[19]:

	PassengerId	Survived	Age	SibSp	Parch	Fare	Age10
Cabin
A10	584.0	0.0	36.000000	0.0	0.00	40.125000	40.000000
A14	476.0	0.0	29.699118	0.0	0.00	52.000000	30.000000
A16	557.0	1.0	48.000000	1.0	0.00	39.600000	50.000000
A19	285.0	0.0	29.699118	0.0	0.00	26.000000	30.000000
A20	600.0	1.0	49.000000	1.0	0.00	56.929200	50.000000
...	...	...	...	...	...	...	...
F33	310.0	1.0	29.000000	0.0	0.00	11.333333	33.333333
F38	777.0	0.0	29.699118	0.0	0.00	7.750000	30.000000
F4	401.5	1.0	2.500000	2.0	1.00	39.000000	10.000000
G6	216.0	0.5	14.750000	0.5	1.25	13.581250	20.000000
T	340.0	0.0	45.000000	0.0	0.00	35.500000	50.000000

147 rows × 7 columns

In [20]:

train.groupby('Cabin').mean().sort_values(by='Survived',ascending=True)

Out[20]:

	PassengerId	Survived	Age	SibSp	Parch	Fare	Age10
Cabin
A10	584.0	0.0	36.000000	0.0	0.0	40.1250	40.0
B86	140.0	0.0	24.000000	0.0	0.0	79.2000	30.0
B94	264.0	0.0	40.000000	0.0	0.0	0.0000	40.0
C110	111.0	0.0	47.000000	0.0	0.0	52.0000	50.0
C111	453.0	0.0	30.000000	0.0	0.0	27.7500	30.0
...	...	...	...	...	...	...	...
C92	652.0	1.0	39.349559	1.0	0.0	89.1042	40.0
B18	427.0	1.0	30.000000	0.0	1.0	57.9792	35.0
C90	711.0	1.0	24.000000	0.0	0.0	49.5042	30.0
D11	766.0	1.0	51.000000	1.0	0.0	77.9583	60.0
C62 C64	701.0	1.0	18.000000	1.0	0.0	227.5250	20.0

147 rows × 7 columns

In [21]:

train.groupby('Cabin').mean().sort_values(by='Fare',ascending=True).iplot(kind='line')

In [22]:

sns.scatterplot(train['Fare'],train['Pclass'])
plt.show()

In [23]:

sns.scatterplot(train['Cabin'],train['Survived'])
plt.show()

In [24]:

traindf=train.drop('Cabin',axis=1,)
traindf.count()

Out[24]:

PassengerId    891
Survived       891
Pclass         891
Name           891
Sex            891
Age            891
SibSp          891
Parch          891
Ticket         891
Fare           891
Embarked       889
Age10          891
dtype: int64

In [41]:

#test
traindf3=train.drop('Cabin',axis=1,)
traindf3.count()

Out[41]:

PassengerId    891
Survived       891
Pclass         891
Name           891
Sex            891
Age            891
SibSp          891
Parch          891
Ticket         891
Fare           891
Embarked       889
Age10          891
dtype: int64

In [42]:

traindf4=traindf3[traindf3['Embarked'].notna()]
traindf4.count()

Out[42]:

PassengerId    889
Survived       889
Pclass         889
Name           889
Sex            889
Age            889
SibSp          889
Parch          889
Ticket         889
Fare           889
Embarked       889
Age10          889
dtype: int64

In [56]:

traindf4['Sex']=='male'

Out[56]:

0       True
1      False
2      False
3      False
4       True
       ...  
886     True
887    False
888    False
889     True
890     True
Name: Sex, Length: 889, dtype: bool

In [64]:

traindf4.loc[traindf4['Sex']=='male', 'Sex'] = 1
traindf4.loc[traindf4['Sex']=='female', 'Sex'] = 0
traindf4.head()

Out[64]:

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Embarked	Age10
0	1	0	3	Braund, Mr. Owen Harris	1	22.0	1	0	A/5 21171	7.2500	S	30
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	0	38.0	1	0	PC 17599	71.2833	C	40
2	3	1	3	Heikkinen, Miss. Laina	0	26.0	0	0	STON/O2. 3101282	7.9250	S	30
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	0	35.0	1	0	113803	53.1000	S	40
4	5	0	3	Allen, Mr. William Henry	1	35.0	0	0	373450	8.0500	S	40

In [71]:

traindf4.loc[traindf4['Embarked']=='S', 'Embarked'] = 1
traindf4.loc[traindf4['Embarked']=='C', 'Embarked'] = 2
traindf4.loc[traindf4['Embarked']=='Q', 'Embarked'] = 3
traindf4.head()

Out[71]:

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Embarked	Age10
0	1	0	3	Braund, Mr. Owen Harris	1	22.0	1	0	A/5 21171	7.2500	1	30
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	0	38.0	1	0	PC 17599	71.2833	2	40
2	3	1	3	Heikkinen, Miss. Laina	0	26.0	0	0	STON/O2. 3101282	7.9250	1	30
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	0	35.0	1	0	113803	53.1000	1	40
4	5	0	3	Allen, Mr. William Henry	1	35.0	0	0	373450	8.0500	1	40

In [76]:

train=traindf4[['Pclass','Sex','Age','SibSp','Parch','Fare','Embarked','Survived']]
X_train=traindf4[['Pclass','Sex','Age','SibSp','Parch','Fare','Embarked']]
y_train=traindf4[['Survived']]

In [80]:

from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split

scaler=StandardScaler()
data_scaled=scaler.fit_transform(train)

X_train,X_test,y_train,y_test=train_test_split(X_train, y_train, test_size=0.3, random_state=0)

lr_clf=LogisticRegression()
lr_clf.fit(X_train,y_train)
lr_preds=lr_clf.predict(X_test)

from sklearn.metrics import accuracy_score, roc_auc_score
accuracy_score(y_test,lr_preds)

C:\Users\flyto\anaconda3\lib\site-packages\sklearn\utils\validation.py:73: DataConversionWarning:

A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().

C:\Users\flyto\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning:

lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression

Out[80]:

1.0

In [81]:

roc_auc_score(y_test,lr_preds)

Out[81]:

1.0