河副太智

複数の分類器で一気に比較

2018年1月19日 by 河副太智 Leave a Comment

複数の分類器

import pandas as pd
from sklearn.model_selection import train_test_split

df = pd.read_csv('train.csv')

df = df.drop(['Cabin','Name','PassengerId','Ticket'],axis=1)
train_X = df.drop('Survived', axis=1)
train_y = df.Survived
(train_X, test_X ,train_y, test_y) = train_test_split(train_X, train_y, test_size = 0.3, random_state = 666)


#決定木
from sklearn.tree import DecisionTreeClassifier
ki = DecisionTreeClassifier(random_state=0).fit(train_X, train_y)
print(ki.score(train_X,train_y))



#ランダムフォレスト
from sklearn.ensemble import RandomForestClassifier
mori = RandomForestClassifier(random_state=0).fit(train_X,train_y)
print(mori.score(train_X,train_y))


#ロジスティック回帰
from sklearn.linear_model import LogisticRegression
logi = LogisticRegression(C=100).fit(train_X,train_y)
print(logi.score(train_X,train_y))


#KNN
from sklearn.neighbors import KNeighborsClassifier
KNN = KNeighborsClassifier(4).fit(train_X,train_y)
print(KNN.score(train_X,train_y))

#SVC
from sklearn.svm import SVC
svc = SVC(probability=True).fit(train_X,train_y)
print(svc.score(train_X,train_y))

#AdaBoostClassifier
from sklearn.ensemble import AdaBoostClassifier
ada = AdaBoostClassifier().fit(train_X,train_y)
print(ada.score(train_X,train_y))

#GradientBoostingClassifier
from sklearn.ensemble import GradientBoostingClassifier
gra = GradientBoostingClassifier().fit(train_X,train_y)
print(gra.score(train_X,train_y))

#GaussianNB
from sklearn.naive_bayes import GaussianNB
gaus = GaussianNB().fit(train_X,train_y)
print(gaus.score(train_X,train_y))

#LinearDiscriminantAnalysis
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
lda = LinearDiscriminantAnalysis().fit(train_X,train_y)
print(lda.score(train_X,train_y))

#QuadraticDiscriminantAnalysis
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
qua = QuadraticDiscriminantAnalysis().fit(train_X,train_y)
print(qua.score(train_X,train_y))

import pandas as pd

from sklearn.model_selection import train_test_split

df = pd.read_csv('train.csv')

df = df.drop(['Cabin','Name','PassengerId','Ticket'],axis=1)

train_X = df.drop('Survived', axis=1)

train_y = df.Survived

(train_X, test_X ,train_y, test_y) = train_test_split(train_X, train_y, test_size = 0.3, random_state = 666)

#決定木

from sklearn.tree import DecisionTreeClassifier

ki = DecisionTreeClassifier(random_state=0).fit(train_X, train_y)

print(ki.score(train_X,train_y))

#ランダムフォレスト

from sklearn.ensemble import RandomForestClassifier

mori = RandomForestClassifier(random_state=0).fit(train_X,train_y)

print(mori.score(train_X,train_y))

#ロジスティック回帰

from sklearn.linear_model import LogisticRegression

logi = LogisticRegression(C=100).fit(train_X,train_y)

print(logi.score(train_X,train_y))

#KNN

from sklearn.neighbors import KNeighborsClassifier

KNN = KNeighborsClassifier(4).fit(train_X,train_y)

print(KNN.score(train_X,train_y))

#SVC

from sklearn.svm import SVC

svc = SVC(probability=True).fit(train_X,train_y)

print(svc.score(train_X,train_y))

#AdaBoostClassifier

from sklearn.ensemble import AdaBoostClassifier

ada = AdaBoostClassifier().fit(train_X,train_y)

print(ada.score(train_X,train_y))

#GradientBoostingClassifier

from sklearn.ensemble import GradientBoostingClassifier

gra = GradientBoostingClassifier().fit(train_X,train_y)

print(gra.score(train_X,train_y))

#GaussianNB

from sklearn.naive_bayes import GaussianNB

gaus = GaussianNB().fit(train_X,train_y)

print(gaus.score(train_X,train_y))

#LinearDiscriminantAnalysis

from sklearn.discriminant_analysis import LinearDiscriminantAnalysis

lda = LinearDiscriminantAnalysis().fit(train_X,train_y)

print(lda.score(train_X,train_y))

#QuadraticDiscriminantAnalysis

from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis

qua = QuadraticDiscriminantAnalysis().fit(train_X,train_y)

print(qua.score(train_X,train_y))

Out[]:
0.982343499197
0.967897271268
0.807383627608
0.796147672552
0.886035313002
0.837881219904
0.898876404494
0.796147672552
0.799357945425
0.813804173355

データフレームでスライスが使えない

2018年1月16日 by 河副太智 Leave a Comment

TypeError: unhashable type: ‘slice’

とエラーが出てデータフレームでスライスが使えない場合は以下のように
ilocを使う

train = pd.read_csv('train.csv', header = 0, dtype={'Age': np.float64})
test  = pd.read_csv('test.csv' , header = 0, dtype={'Age': np.float64})
full_data = [train, test]


dataset = pd.DataFrame(np.random.rand(10, 10))#random無くてもいける
y=train.iloc[0::, 1::]
X=train.iloc[0::, 0]

train = pd.read_csv('train.csv', header = 0, dtype={'Age': np.float64})

test = pd.read_csv('test.csv' , header = 0, dtype={'Age': np.float64})

full_data = [train, test]

dataset = pd.DataFrame(np.random.rand(10, 10))#random無くてもいける

y=train.iloc[0::, 1::]

X=train.iloc[0::, 0]

指定の文字を別の文字に置き換える

2018年1月16日 by 河副太智 Leave a Comment

for dataset in full_data:
    dataset['Title'] = dataset['Title'].replace(['Lady', 'Countess','Capt', 'Col',\
 	'Don', 'Dr', 'Major', 'Rev', 'Sir', 'Jonkheer', 'Dona'], 'Rare')

    dataset['Title'] = dataset['Title'].replace('Mlle', 'Miss')
    dataset['Title'] = dataset['Title'].replace('Ms', 'Miss')
    dataset['Title'] = dataset['Title'].replace('Mme', 'Mrs')

print (train[['Title', 'Survived']].groupby(['Title'], as_index=False).mean())

for dataset in full_data:

dataset['Title'] = dataset['Title'].replace(['Lady', 'Countess','Capt', 'Col',\

'Don', 'Dr', 'Major', 'Rev', 'Sir', 'Jonkheer', 'Dona'], 'Rare')

dataset['Title'] = dataset['Title'].replace('Mlle', 'Miss')

dataset['Title'] = dataset['Title'].replace('Ms', 'Miss')

dataset['Title'] = dataset['Title'].replace('Mme', 'Mrs')

print (train[['Title', 'Survived']].groupby(['Title'], as_index=False).mean())

意味の同じ要素を一つに統合

2018年1月16日 by 河副太智 Leave a Comment

‘Ms’, ‘Miss’の２つは同じ意味なのでこういったものを一つに統合

O’Driscoll, Miss. Bridget

Samaan, Mr. Youssef

Arnold-Franchi, Mrs. Josef (Josefine Franchi)

Panula, Master. Juha Niilo

Nosworthy, Mr. Richard Cater

Harper, Mrs. Henry Sleeper (Myna Haxtun)

Faunthorpe, Mrs. Lizzie (Elizabeth Anne Wilkinson)

Ostby, Mr. Engelhart Cornelius

Woolner, Mr. Hugh

def get_title(name):
	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 ""

for dataset in full_data:
    dataset['Title'] = dataset['Name'].apply(get_title)

print(pd.crosstab(train['Title'], train['Sex']))

def get_title(name):

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 ""

for dataset in full_data:

dataset['Title'] = dataset['Name'].apply(get_title)

print(pd.crosstab(train['Title'], train['Sex']))

上記の結果以下のように名前のタイトルの一覧が出る

Sex       female  male
Title                 
Capt           0     1
Col            0     2
Countess       1     0
Don            0     1
Dr             1     6
Jonkheer       0     1
Lady           1     0
Major          0     2
Master         0    40
Miss         182     0
Mlle           2     0
Mme            1     0
Mr             0   517
Mrs          125     0
Ms             1     0
Rev            0     6
Sir            0     1

Sex female male

Title

Capt 0 1

Col 0 2

Countess 1 0

Don 0 1

Dr 1 6

Jonkheer 0 1

Lady 1 0

Major 0 2

Master 0 40

Miss 182 0

Mlle 2 0

Mme 1 0

Mr 0 517

Mrs 125 0

Ms 1 0

Rev 0 6

Sir 0 1

同じ意味の物を統合する

for dataset in full_data:
    dataset['Title'] = dataset['Title'].replace(['Lady', 'Countess','Capt', 'Col',\
 	'Don', 'Dr', 'Major', 'Rev', 'Sir', 'Jonkheer', 'Dona'], 'Rare')

    dataset['Title'] = dataset['Title'].replace('Mlle', 'Miss')
    dataset['Title'] = dataset['Title'].replace('Ms', 'Miss')
    dataset['Title'] = dataset['Title'].replace('Mme', 'Mrs')

print (train[['Title', 'Survived']].groupby(['Title'], as_index=False).mean())

for dataset in full_data:

dataset['Title'] = dataset['Title'].replace(['Lady', 'Countess','Capt', 'Col',\

'Don', 'Dr', 'Major', 'Rev', 'Sir', 'Jonkheer', 'Dona'], 'Rare')

dataset['Title'] = dataset['Title'].replace('Mlle', 'Miss')

dataset['Title'] = dataset['Title'].replace('Ms', 'Miss')

dataset['Title'] = dataset['Title'].replace('Mme', 'Mrs')

print (train[['Title', 'Survived']].groupby(['Title'], as_index=False).mean())

結果

   Title  Survived
0  Master  0.575000
1    Miss  0.702703
2      Mr  0.156673
3     Mrs  0.793651
4    Rare  0.347826

Title Survived

0 Master 0.575000

1 Miss 0.702703

2 Mr 0.156673

3 Mrs 0.793651

4 Rare 0.347826

データセットの数、カラム、型の一覧表示

2018年1月16日 by 河副太智 Leave a Comment

train.info()

1	train.info()

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
None

決定木

2018年1月16日 by 河副太智 Leave a Comment

決定木

train_X = df.drop('Survived', axis=1)
train_y = df.Survived
(train_X, test_X ,train_y, test_y) = train_test_split(train_X, train_y, test_size = 0.3, random_state = 666)

#決定木
clf = DecisionTreeClassifier(random_state=0)
clf = clf.fit(train_X, train_y)
pred = clf.predict(test_X)

#決定木のモデルスコア
fpr, tpr, thresholds = roc_curve(test_y, pred, pos_label=1)
auc(fpr, tpr)
accuracy_score(pred, test_y)

train_X = df.drop('Survived', axis=1)

train_y = df.Survived

(train_X, test_X ,train_y, test_y) = train_test_split(train_X, train_y, test_size = 0.3, random_state = 666)

#決定木

clf = DecisionTreeClassifier(random_state=0)

clf = clf.fit(train_X, train_y)

pred = clf.predict(test_X)

#決定木のモデルスコア

fpr, tpr, thresholds = roc_curve(test_y, pred, pos_label=1)

auc(fpr, tpr)

accuracy_score(pred, test_y)

河副 太智

河副太智