機械学習のデータの前処理で、pandasを使う派とデータベースを使う派がいますが、pandasの方は使いにくくてよくわからないので練習します。ついでに得意なSQLの方も使って同じようにデータを加工してみます。
目次
使用するデータセット
以下のサイトからダウンロードした、heart disease に関するデータセットを使用します。
https://www.kaggle.com/datasets/johnsmith88/heart-disease-dataset?resource=download
CSVファイルの中身はこんな感じになっています。
Pandasの場合
read_csvメソッドを使用することで、データの読み込みを一行でおこなってくれるようです。
import pandas as pd
data = pd.read_csv('heart.csv')
X = data.drop('target',axis = 1)
y = data['target']
>>>
age sex cp trestbps chol fbs restecg thalach exang oldpeak slope ca thal
0 52 1 0 125 212 0 1 168 0 1.0 2 2 3
1 53 1 0 140 203 1 0 155 1 3.1 0 0 3
2 70 1 0 145 174 0 1 125 1 2.6 0 0 3
3 61 1 0 148 203 0 1 161 0 0.0 2 1 3
4 62 0 0 138 294 1 1 106 0 1.9 1 3 2
... ... ... .. ... ... ... ... ... ... ... ... .. ...
1020 59 1 1 140 221 0 1 164 1 0.0 2 0 2
1021 60 1 0 125 258 0 0 141 1 2.8 1 1 3
1022 47 1 0 110 275 0 0 118 1 1.0 1 1 2
1023 50 0 0 110 254 0 0 159 0 0.0 2 0 2
1024 54 1 0 120 188 0 1 113 0 1.4 1 1 3
[1025 rows x 13 columns]
0 0
1 0
2 0
3 0
4 0
..
1020 1
1021 0
1022 0
1023 1
1024 0
Name: target, Length: 1025, dtype: int64上記の説明変数と従属変数を使用して、sklearnのランダムフォレストを使ってみます。
from sklearn.ensemble import RandomForestClassifier
model = RandomForestClassifier()
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.5)
print(X_train)
model.fit(X_train,y_train)
#prediction
y_preds = model.predict(X_test)
print(y_preds)
#get max percent
print(model.score(X_train,y_train))
print(model.score(X_test,y_test))
>>>
age sex cp trestbps chol fbs restecg thalach exang oldpeak slope ca thal
303 60 1 0 145 282 0 0 142 1 2.8 1 2 3
383 58 1 0 150 270 0 0 111 1 0.8 2 0 3
708 60 0 2 120 178 1 1 96 0 0.0 2 0 2
213 43 1 2 130 315 0 1 162 0 1.9 2 1 2
614 51 0 0 130 305 0 1 142 1 1.2 1 0 3
.. ... ... .. ... ... ... ... ... ... ... ... .. ...
507 41 0 1 130 204 0 0 172 0 1.4 2 0 2
347 54 0 2 108 267 0 0 167 0 0.0 2 0 2
341 44 1 2 120 226 0 1 169 0 0.0 2 0 2
53 49 1 2 120 188 0 1 139 0 2.0 1 3 3
775 51 1 2 100 222 0 1 143 1 1.2 1 0 2
[512 rows x 13 columns]
[0 1 1 0 0 0 0 1 1 1 1 0 0 0 0 1 1 0 0 1 0 0 1 1 0 0 0 0 0 1 0 0 0 1 0 1 1
0 0 0 0 1 1 0 0 0 0 1 0 1 1 1 0 1 0 0 1 0 1 0 1 0 1 0 1 0 1 1 1 0 1 0 0 1
0 1 0 0 1 0 0 0 1 1 0 0 0 0 1 0 0 0 1 0 1 1 0 0 1 0 1 1 1 1 0 0 1 0 0 1 0
1 1 1 0 1 0 1 1 1 1 1 0 1 0 0 0 1 1 1 1 0 1 0 0 1 0 1 1 0 1 1 1 0 0 1 1 1
1 1 0 1 0 1 0 0 1 1 1 0 0 1 0 0 1 1 1 0 1 1 0 1 0 0 0 0 0 0 0 1 1 0 1 0 1
1 0 0 1 0 1 1 1 0 0 1 1 1 1 1 1 1 1 1 1 0 1 0 0 1 0 1 0 0 1 1 1 0 1 1 0 1
0 1 0 0 0 0 1 0 1 1 0 0 1 1 1 1 1 0 0 0 1 1 0 0 0 1 0 0 1 1 0 1 0 0 0 1 0
0 0 1 0 0 0 1 0 0 0 1 1 1 0 1 1 0 1 0 0 1 1 1 1 1 1 0 1 1 1 0 0 0 1 0 1 0
1 1 1 0 0 0 1 0 1 0 1 0 1 1 0 1 1 0 1 0 1 1 1 1 1 1 0 0 1 1 1 0 1 1 0 1 1
1 1 1 0 1 1 0 1 0 1 0 1 1 1 1 1 0 1 0 0 0 0 1 0 0 1 0 1 0 0 0 1 1 1 1 0 1
1 1 1 1 1 1 1 0 0 0 0 0 1 0 1 0 0 1 1 0 1 1 1 0 0 1 1 1 0 1 0 1 0 1 1 1 0
0 0 1 1 0 0 0 0 1 0 0 0 0 1 0 1 0 0 0 1 0 0 1 1 1 1 1 0 1 1 0 1 0 0 0 0 0
0 1 1 0 1 0 0 0 0 0 1 0 0 0 1 1 1 0 0 0 0 0 1 1 1 0 0 0 1 0 0 1 1 0 1 1 0
1 0 0 0 1 1 0 1 1 0 0 1 1 0 0 0 1 1 1 1 1 0 0 1 1 1 0 1 1 1 0 1]
1.0
0.9688109161793372どうやらsklearnのメソッドはpandasデータフレームを引数として受け取ることが前提のようです。他の受け渡し方もあるかもしれませんが、まだ把握できていません。
いずれにせよ、csvの読み込みから数行でランダムフォレストまで実行できてしまうようです。
MySQLの場合
以下のクラスを作成して、pythonからMySQLに接続して操作します。
from mysql import connector
import user
class Table:
def __init__(self,table_name:str,columns:list[str]) -> None:
self.table_name:str = table_name
self.columns : list[str] = ['id INT PRIMARY KEY AUTO_INCREMENT'] + columns
def get_columns(self) -> list:
return [i.split(" ")[0] for i in self.columns][1:]
def get_table_name(self) -> str:
return self.table_name
class Database:
def __init__(self,db_name:str)-> None:
self.show_exception:bool = True
self.db_name : str = db_name
self.host_name : str = 'localhost'
self.user_name : str = 'root'
self.user_password : str = f'{user.password}'
self.mysql_connection = self.create_connection()
self.create_database()
self.db_connection = self.create_database_connection()
def create_connection(self) ->connector.connection.MySQLConnection:
connection = None
try:
connection = connector.connect(
host=self.host_name,
user=self.user_name,
password=self.user_password,
)
if connection.is_connected:
print("Connection created successfully.")
except Exception as e:
if self.show_exception:
print(f"Exception caught -> {e}")
return connection
def create_database(self) -> connector.connection.MySQLConnection:
c = self.mysql_connection.cursor()
try:
c.execute(f'CREATE database {self.db_name}')
print(f"Database {self.db_name} created successfully.")
except Exception as e:
print(f"Caution: Database {self.db_name} already exists.")
if self.show_exception:
print(f"Exception caught -> {e}")
def create_database_connection(self) -> connector.connection.MySQLConnection:
connection = None
try:
connection = connector.connect(
host=self.host_name,
user=self.user_name,
password=self.user_password,
database = self.db_name
)
if connection.is_connected:
print(f"Connected to database {self.db_name}...")
except Exception as e:
if self.show_exception:
print(f"Exception caught -> {e}")
return connection
def execute(self,query:str) -> connector:
c = self.db_connection.cursor()
try:
c.execute(query)
self.db_connection.commit()
print(f"Query ({query}) excuted successfully.")
except Exception as e:
if self.show_exception:
print(f"Exception caught -> {e}")
print("->Could not execute {}".format(query.replace('\n','')))
return c
def drop_database(self,toDrop) -> None:
if toDrop:
self.execute(f"DROP DATABASE {self.db_name}")
else:
pass データの格納
from main import Database, Table
db = Database('db')
file_path = 'heart.csv'
with open(file=file_path,mode='r', encoding='utf-8-sig') as fp:
lines = fp.readlines()
lines = [[i.replace('\n','') for i in j.split(',')] for j in lines]
columns = [f'{i} INT' if i.count('.') == 0 else f'{i} FLOAT' for i in lines[0]]
table1 = Table(table_name='Table1',columns=columns)
db.execute(f'CREATE TABLE {table1.get_table_name()} ({",".join(table1.columns)})')
for i in lines[1:]:
values = ','.join(i)
db.execute(f'INSERT INTO {table1.get_table_name()} ({",".join(table1.get_columns())}) VALUES({values})')
db.drop_database(False)実行結果
MySQL [db]> desc table1;
+----------+------+------+-----+---------+----------------+
| Field | Type | Null | Key | Default | Extra |
+----------+------+------+-----+---------+----------------+
| id | int | NO | PRI | NULL | auto_increment |
| age | int | YES | | NULL | |
| sex | int | YES | | NULL | |
| cp | int | YES | | NULL | |
| trestbps | int | YES | | NULL | |
| chol | int | YES | | NULL | |
| fbs | int | YES | | NULL | |
| restecg | int | YES | | NULL | |
| thalach | int | YES | | NULL | |
| exang | int | YES | | NULL | |
| oldpeak | int | YES | | NULL | |
| slope | int | YES | | NULL | |
| ca | int | YES | | NULL | |
| thal | int | YES | | NULL | |
| target | int | YES | | NULL | |
+----------+------+------+-----+---------+----------------+
15 rows in set (0.006 sec)
MySQL [db]> select * from table1;
+------+------+------+------+----------+------+------+---------+---------+-------+---------+-------+------+------+--------+
| id | age | sex | cp | trestbps | chol | fbs | restecg | thalach | exang | oldpeak | slope | ca | thal | target |
+------+------+------+------+----------+------+------+---------+---------+-------+---------+-------+------+------+--------+
| 1 | 52 | 1 | 0 | 125 | 212 | 0 | 1 | 168 | 0 | 1 | 2 | 2 | 3 | 0 |
| 2 | 53 | 1 | 0 | 140 | 203 | 1 | 0 | 155 | 1 | 3 | 0 | 0 | 3 | 0 |
| 3 | 70 | 1 | 0 | 145 | 174 | 0 | 1 | 125 | 1 | 3 | 0 | 0 | 3 | 0 |
| 4 | 61 | 1 | 0 | 148 | 203 | 0 | 1 | 161 | 0 | 0 | 2 | 1 | 3 | 0 |
| 5 | 62 | 0 | 0 | 138 | 294 | 1 | 1 | 106 | 0 | 2 | 1 | 3 | 2 | 0 |
| 6 | 58 | 0 | 0 | 100 | 248 | 0 | 0 | 122 | 0 | 1 | 1 | 0 | 2 | 1 |
| 7 | 58 | 1 | 0 | 114 | 318 | 0 | 2 | 140 | 0 | 4 | 0 | 3 | 1 | 0 |
| 8 | 55 | 1 | 0 | 160 | 289 | 0 | 0 | 145 | 1 | 1 | 1 | 1 | 3 | 0 |
| 9 | 46 | 1 | 0 | 120 | 249 | 0 | 0 | 144 | 0 | 1 | 2 | 0 | 3 | 0 |
| 10 | 54 | 1 | 0 | 122 | 286 | 0 | 0 | 116 | 1 | 3 | 1 | 2 | 2 | 0 |
| 11 | 71 | 0 | 0 | 112 | 149 | 0 | 1 | 125 | 0 | 2 | 1 | 0 | 2 | 1 |
| 12 | 43 | 0 | 0 | 132 | 341 | 1 | 0 | 136 | 1 | 3 | 1 | 0 | 3 | 0 |
| 13 | 34 | 0 | 1 | 118 | 210 | 0 | 1 | 192 | 0 | 1 | 2 | 0 | 2 | 1 |
| 14 | 51 | 1 | 0 | 140 | 298 | 0 | 1 | 122 | 1 | 4 | 1 | 3 | 3 | 0 |
| 15 | 52 | 1 | 0 | 128 | 204 | 1 | 1 | 156 | 1 | 1 | 1 | 0 | 0 | 0 |
| 16 | 34 | 0 | 1 | 118 | 210 | 0 | 1 | 192 | 0 | 1 | 2 | 0 | 2 | 1 |
| 17 | 51 | 0 | 2 | 140 | 308 | 0 | 0 | 142 | 0 | 2 | 2 | 1 | 2 | 1 |
| 18 | 54 | 1 | 0 | 124 | 266 | 0 | 0 | 109 | 1 | 2 | 1 | 1 | 3 | 0 |
| 19 | 50 | 0 | 1 | 120 | 244 | 0 | 1 | 162 | 0 | 1 | 2 | 0 | 2 | 1 |
| 20 | 58 | 1 | 2 | 140 | 211 | 1 | 0 | 165 | 0 | 0 | 2 | 0 | 2 | 1 |
...........................................................................................................................
| 999 | 42 | 1 | 0 | 136 | 315 | 0 | 1 | 125 | 1 | 2 | 1 | 0 | 1 | 0 |
| 1000 | 67 | 1 | 0 | 125 | 254 | 1 | 1 | 163 | 0 | 0 | 1 | 2 | 3 | 0 |
| 1001 | 64 | 1 | 0 | 145 | 212 | 0 | 0 | 132 | 0 | 2 | 1 | 2 | 1 | 0 |
| 1002 | 42 | 1 | 0 | 140 | 226 | 0 | 1 | 178 | 0 | 0 | 2 | 0 | 2 | 1 |
| 1003 | 66 | 1 | 0 | 112 | 212 | 0 | 0 | 132 | 1 | 0 | 2 | 1 | 2 | 0 |
| 1004 | 52 | 1 | 0 | 108 | 233 | 1 | 1 | 147 | 0 | 0 | 2 | 3 | 3 | 1 |
| 1005 | 51 | 0 | 2 | 140 | 308 | 0 | 0 | 142 | 0 | 2 | 2 | 1 | 2 | 1 |
| 1006 | 55 | 0 | 0 | 128 | 205 | 0 | 2 | 130 | 1 | 2 | 1 | 1 | 3 | 0 |
| 1007 | 58 | 1 | 2 | 140 | 211 | 1 | 0 | 165 | 0 | 0 | 2 | 0 | 2 | 1 |
| 1008 | 56 | 1 | 3 | 120 | 193 | 0 | 0 | 162 | 0 | 2 | 1 | 0 | 3 | 1 |
| 1009 | 42 | 1 | 1 | 120 | 295 | 0 | 1 | 162 | 0 | 0 | 2 | 0 | 2 | 1 |
| 1010 | 40 | 1 | 0 | 152 | 223 | 0 | 1 | 181 | 0 | 0 | 2 | 0 | 3 | 0 |
| 1011 | 51 | 1 | 0 | 140 | 299 | 0 | 1 | 173 | 1 | 2 | 2 | 0 | 3 | 0 |
| 1012 | 45 | 1 | 1 | 128 | 308 | 0 | 0 | 170 | 0 | 0 | 2 | 0 | 2 | 1 |
| 1013 | 48 | 1 | 1 | 110 | 229 | 0 | 1 | 168 | 0 | 1 | 0 | 0 | 3 | 0 |
| 1014 | 58 | 1 | 0 | 114 | 318 | 0 | 2 | 140 | 0 | 4 | 0 | 3 | 1 | 0 |
| 1015 | 44 | 0 | 2 | 108 | 141 | 0 | 1 | 175 | 0 | 1 | 1 | 0 | 2 | 1 |
| 1016 | 58 | 1 | 0 | 128 | 216 | 0 | 0 | 131 | 1 | 2 | 1 | 3 | 3 | 0 |
| 1017 | 65 | 1 | 3 | 138 | 282 | 1 | 0 | 174 | 0 | 1 | 1 | 1 | 2 | 0 |
| 1018 | 53 | 1 | 0 | 123 | 282 | 0 | 1 | 95 | 1 | 2 | 1 | 2 | 3 | 0 |
| 1019 | 41 | 1 | 0 | 110 | 172 | 0 | 0 | 158 | 0 | 0 | 2 | 0 | 3 | 0 |
| 1020 | 47 | 1 | 0 | 112 | 204 | 0 | 1 | 143 | 0 | 0 | 2 | 0 | 2 | 1 |
| 1021 | 59 | 1 | 1 | 140 | 221 | 0 | 1 | 164 | 1 | 0 | 2 | 0 | 2 | 1 |
| 1022 | 60 | 1 | 0 | 125 | 258 | 0 | 0 | 141 | 1 | 3 | 1 | 1 | 3 | 0 |
| 1023 | 47 | 1 | 0 | 110 | 275 | 0 | 0 | 118 | 1 | 1 | 1 | 1 | 2 | 0 |
| 1024 | 50 | 0 | 0 | 110 | 254 | 0 | 0 | 159 | 0 | 0 | 2 | 0 | 2 | 1 |
| 1025 | 54 | 1 | 0 | 120 | 188 | 0 | 1 | 113 | 0 | 1 | 1 | 1 | 3 | 0 |
+------+------+------+------+----------+------+------+---------+---------+-------+---------+-------+------+------+--------+
1025 rows in set (0.005 sec)データ格納のテンプレート
今後のために、上記の操作をテンプレート化しておきます。
from mysql import connector
import user
class Table:
def __init__(self,table_name:str,columns:list[str]) -> None:
self.table_name:str = table_name
self.columns : list[str] = ['id INT PRIMARY KEY AUTO_INCREMENT'] + columns
def get_columns(self) -> list:
return [i.split(" ")[0] for i in self.columns][1:]
def get_table_name(self) -> str:
return self.table_name
class Database:
def __init__(self,db_name:str)-> None:
self.show_exception:bool = True
self.db_name : str = db_name
self.host_name : str = 'localhost'
self.user_name : str = 'root'
self.user_password : str = f'{user.password}'
self.mysql_connection = self.create_connection()
self.create_database()
self.db_connection = self.create_database_connection()
def create_connection(self) ->connector.connection.MySQLConnection:
connection = None
try:
connection = connector.connect(
host=self.host_name,
user=self.user_name,
password=self.user_password,
)
if connection.is_connected:
print("Connection created successfully.")
except Exception as e:
if self.show_exception:
print(f"Exception caught -> {e}")
return connection
def create_database(self) -> connector.connection.MySQLConnection:
c = self.mysql_connection.cursor()
try:
c.execute(f'CREATE database {self.db_name}')
print(f"Database {self.db_name} created successfully.")
except Exception as e:
print(f"Caution: Database {self.db_name} already exists.")
if self.show_exception:
print(f"Exception caught -> {e}")
def create_database_connection(self) -> connector.connection.MySQLConnection:
connection = None
try:
connection = connector.connect(
host=self.host_name,
user=self.user_name,
password=self.user_password,
database = self.db_name
)
if connection.is_connected:
print(f"Connected to database {self.db_name}...")
except Exception as e:
if self.show_exception:
print(f"Exception caught -> {e}")
return connection
def execute(self,query:str) -> connector:
c = self.db_connection.cursor()
try:
c.execute(query)
self.db_connection.commit()
print(f"Query ({query}) excuted successfully.")
except Exception as e:
if self.show_exception:
print(f"Exception caught -> {e}")
print("->Could not execute {}".format(query.replace('\n','')))
return c
def drop_database(self,toDrop) -> None:
if toDrop:
self.execute(f"DROP DATABASE {self.db_name}")
else:
pass
def extract_data(csv_path:str,db_name:str,table_name:str = 'table1',toDrop:bool = False,onHold:bool = False):
db = Database(db_name)
file_path = csv_path
with open(file=file_path,mode='r', encoding='utf-8-sig') as fp:
lines = fp.readlines()
lines = [[i.replace('\n','') for i in j.split(',')] for j in lines]
##############################################################################
columns = [f'{i} INT' if i.count('.') == 0 else f'{i} FLOAT' for i in lines[0]]
##############################################################################
table1 = Table(table_name=table_name,columns=columns)
if not onHold:
db.execute(f'CREATE TABLE {table1.get_table_name()} ({",".join(table1.columns)})')
for i in lines[1:]:
values = ','.join(i)
db.execute(f'INSERT INTO {table1.get_table_name()} ({",".join(table1.get_columns())}) VALUES({values})')
db.drop_database(toDrop)
return db,table1ランダムフォレストモデルの使用
MySQLから情報を引っ張ってくる練習をするために、上記データに対してsklearnのランダムフォレストモデルを使ってみます。
今のところ、引数としてpandasオブジェクトを渡すということがわかっているので、結局はpandasを使用しますが、MySQLからデータを取ってくる作業の練習をおこなってみます。
"""
db = Database('db')
file_path = 'heart.csv'
with open(file=file_path,mode='r', encoding='utf-8-sig') as fp:
lines = fp.readlines()
lines = [[i.replace('\n','') for i in j.split(',')] for j in lines]
columns = [f'{i} INT' if i.count('.') == 0 else f'{i} FLOAT' for i in lines[0]]
table1 = Table(table_name='Table1',columns=columns)
"""
import pandas as pd
data = db.execute(f'SELECT * FROM {table1.get_table_name()}').fetchall()
data = [i[1:] for i in data]
df = pd.DataFrame(data)
df = df.rename(columns={i:n for i,n in enumerate(table1.get_columns())})
print(df)
>>>
age sex cp trestbps chol fbs restecg thalach exang oldpeak slope ca thal target
0 52 1 0 125 212 0 1 168 0 1 2 2 3 0
1 53 1 0 140 203 1 0 155 1 3 0 0 3 0
2 70 1 0 145 174 0 1 125 1 3 0 0 3 0
3 61 1 0 148 203 0 1 161 0 0 2 1 3 0
4 62 0 0 138 294 1 1 106 0 2 1 3 2 0
... ... ... .. ... ... ... ... ... ... ... ... .. ... ...
1020 59 1 1 140 221 0 1 164 1 0 2 0 2 1
1021 60 1 0 125 258 0 0 141 1 3 1 1 3 0
1022 47 1 0 110 275 0 0 118 1 1 1 1 2 0
1023 50 0 0 110 254 0 0 159 0 0 2 0 2 1
1024 54 1 0 120 188 0 1 113 0 1 1 1 3 0
[1025 rows x 14 columns]Pandasオブジェクトができたのでランダムフォレストにかけます。
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
model = RandomForestClassifier()
X = df.drop('target',axis = 1)
y = df['target']
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.5)
print(X_train)
model.fit(X_train,y_train)
#prediction
y_preds = model.predict(X_test)
print(y_preds)
#get max percent
print(model.score(X_train,y_train))
print(model.score(X_test,y_test))
>>>
age sex cp trestbps chol fbs restecg thalach exang oldpeak slope ca thal target
0 52 1 0 125 212 0 1 168 0 1 2 2 3 0
1 53 1 0 140 203 1 0 155 1 3 0 0 3 0
2 70 1 0 145 174 0 1 125 1 3 0 0 3 0
3 61 1 0 148 203 0 1 161 0 0 2 1 3 0
4 62 0 0 138 294 1 1 106 0 2 1 3 2 0
... ... ... .. ... ... ... ... ... ... ... ... .. ... ...
1020 59 1 1 140 221 0 1 164 1 0 2 0 2 1
1021 60 1 0 125 258 0 0 141 1 3 1 1 3 0
1022 47 1 0 110 275 0 0 118 1 1 1 1 2 0
1023 50 0 0 110 254 0 0 159 0 0 2 0 2 1
1024 54 1 0 120 188 0 1 113 0 1 1 1 3 0
[1025 rows x 14 columns]
age sex cp trestbps chol fbs restecg thalach exang oldpeak slope ca thal
458 43 1 0 150 247 0 1 171 0 2 2 0 2
158 67 0 2 115 564 0 0 160 0 2 1 0 3
850 58 1 1 120 284 0 0 160 0 2 1 0 2
489 61 1 2 150 243 1 1 137 1 1 1 0 2
889 63 0 0 150 407 0 0 154 0 4 1 3 3
.. ... ... .. ... ... ... ... ... ... ... ... .. ...
212 50 1 0 150 243 0 0 128 0 3 1 0 3
143 34 1 3 118 182 0 0 174 0 0 2 0 2
146 51 0 2 120 295 0 0 157 0 1 2 0 2
962 52 1 0 108 233 1 1 147 0 0 2 3 3
638 65 1 3 138 282 1 0 174 0 1 1 1 2
[512 rows x 13 columns]
[1 0 1 0 1 1 1 1 1 0 1 0 0 1 1 1 1 1 1 0 1 0 0 1 0 0 0 0 1 1 0 1 0 0 0 1 0
0 0 1 1 1 0 0 0 1 1 0 0 1 1 0 1 1 0 0 1 0 1 0 0 0 1 0 0 1 0 0 1 0 1 0 0 0
1 0 0 1 1 0 0 1 1 1 1 0 1 1 1 1 0 1 1 1 0 0 1 0 0 1 0 0 1 0 1 1 0 1 0 0 1
1 1 0 1 1 1 1 0 0 0 0 0 1 0 1 0 0 1 1 1 1 1 0 0 0 1 1 0 1 1 1 0 1 1 1 1 1
0 0 0 1 1 1 1 0 0 1 1 0 1 0 0 0 1 0 0 0 0 0 1 1 1 1 1 1 0 1 0 0 0 1 1 0 1
0 1 1 1 0 1 1 0 0 1 1 0 1 1 1 1 1 1 1 0 1 0 1 0 0 0 0 1 1 1 0 1 0 0 0 0 0
0 1 1 1 1 1 0 0 1 1 0 0 1 0 1 0 1 1 0 0 0 1 1 0 1 0 1 0 1 1 0 1 0 1 1 0 0
0 1 1 1 1 1 0 0 0 1 0 1 1 1 1 1 1 0 0 0 1 0 0 0 1 1 1 0 1 1 0 1 0 0 1 0 0
1 0 1 0 0 1 0 1 1 1 1 1 0 0 1 1 0 0 1 0 1 1 0 1 0 1 0 0 1 0 1 0 0 1 0 1 0
0 1 1 1 0 1 0 0 0 1 1 0 0 0 1 0 0 1 1 0 1 1 1 0 1 0 1 1 0 0 1 1 1 1 0 0 1
1 0 1 0 0 0 0 1 1 0 1 0 1 1 0 0 1 0 0 0 1 0 0 1 0 1 1 0 1 0 0 0 0 1 1 0 1
0 1 0 0 0 1 1 1 0 0 1 1 0 1 0 1 0 0 1 0 0 0 0 1 1 1 1 1 0 0 1 0 0 0 0 0 1
1 1 1 1 0 0 0 1 1 0 0 1 0 0 0 1 1 1 0 0 0 0 1 1 0 0 0 0 1 0 0 0 0 0 1 0 0
1 0 1 1 0 0 1 0 1 0 0 1 1 1 0 0 1 1 1 0 1 1 1 1 0 1 1 1 0 0 1 1]
1.0
0.9688109161793372Pandas単体より冗長にはなりますが、大量のデータを別の場所にきれいに保管しておけると言うのはMySQLの強みだと思います。
