自动化机器学习pycaret： PyCaret Basic Auto Classification LightGBM

from IPython.display import clear_output
!pip3 install pycaret --user
clear_output()

!pip install numpy==1.20.0

import numpy as np
import pandas as pd 
 
import random
import os 
 
from pycaret.classification import *

TRAIN_PATH = "../input/titanic/train.csv"
TEST_PATH = "../input/titanic/test.csv"
SAMPLE_SUBMISSION_PATH = "../input/titanic/gender_submission.csv"
SUBMISSION_PATH = "submission.csv"
 
ID = "PassengerId"
TARGET = "Survived"
 
SEED = 2022
 
def seed_everything(seed: int = SEED):
    random.seed(seed)
    np.random.seed(seed)
    os.environ["PYTHONHASHSEED"] = str(seed)
    
seed_everything()

import pandas as pd
train = pd.read_csv(TRAIN_PATH)
test = pd.read_csv(TEST_PATH)
test

 

 

 

setup(
    data=train,
    target=TARGET,
    silent=True
)

 

({'lr': ,
  'knn': ,
  'nb': ,
  'dt': ,
  'svm': ,
  'rbfsvm': ,
  'gpc': ,
  'mlp': ,
  'ridge': ,
  'rf': ,
  'qda': ,
  'ada': ,
  'gbc': ,
  'lda': ,
  'et': ,
  'xgboost': ,
  'lightgbm': ,
  'catboost': ,
  'dummy': },
 True,
 150    0
 547    1
 125    1
 779    1
 183    1
       ..
 370    1
 317    0
 351    0
 339    0
 289    1
 Name: Survived, Length: 623, dtype: int64,
 10,
 8860,
 '88e1',
 Pipeline(memory=None, steps=[('empty_step', 'passthrough')], verbose=False),
 False,
            Age       Fare  Pclass_1  Pclass_2  Pclass_3  \
 0    22.000000   7.250000       0.0       0.0       1.0   
 1    38.000000  71.283302       1.0       0.0       0.0   
 2    26.000000   7.925000       0.0       0.0       1.0   
 3    35.000000  53.099998       1.0       0.0       0.0   
 4    35.000000   8.050000       0.0       0.0       1.0   
 ..         ...        ...       ...       ...       ...   
 886  27.000000  13.000000       0.0       1.0       0.0   
 887  19.000000  30.000000       1.0       0.0       0.0   
 888  29.466112  23.450001       0.0       0.0       1.0   
 889  26.000000  30.000000       1.0       0.0       0.0   
 890  32.000000   7.750000       0.0       0.0       1.0   
 
      Name_Aks Mrs. Sam (Leah Rosen)  Name_Albimona Mr. Nassef Cassem  \
 0                               0.0                              0.0   
 1                               0.0                              0.0   
 2                               0.0                              0.0   
 3                               0.0                              0.0   
 4                               0.0                              0.0   
 ..                              ...                              ...   
 886                             0.0                              0.0   
 887                             0.0                              0.0   
 888                             0.0                              0.0   
 889                             0.0                              0.0   
 890                             0.0                              0.0   
 
      Name_Ali Mr. Ahmed  Name_Allen Mr. William Henry  \
 0                   0.0                           0.0   
 1                   0.0                           0.0   
 2                   0.0                           0.0   
 3                   0.0                           0.0   
 4                   0.0                           1.0   
 ..                  ...                           ...   
 886                 0.0                           0.0   
 887                 0.0                           0.0   
 888                 0.0                           0.0   
 889                 0.0                           0.0   
 890                 0.0                           0.0   

model = create_model('lightgbm')

tuneModel = tune_model(model,optimize = 'AUC')

 

plot_model(tuneModel)

 

plot_model(tuneModel, plot='feature')