0 
import pandas as pd
df = pd.read_csv("/content/drive/MyDrive/kaglee/pokemon_alopez247.csv")

我对数据进行了预处理。

df.columns
Index(['dark', 'dragon', 'electric', 'fairy', 'fighting', 'fire', 'flying',
       'ghost', 'grass', 'ground', 'ice', 'normal', 'poison', 'psychic',
       'rock', 'steel', 'Ditto', 'bug', 'dragon', 'fairy', 'field', 'flying',
       'grass', 'human-Like', 'mineral', 'monster', 'water_1', 'water_2',
       'water_3', 'legend', 'Color_Blue', 'Color_Brown', 'Color_Green',
       'Color_Grey', 'Color_Pink', 'Color_Purple', 'Color_Red', 'Color_White',
       'Color_Yellow', 'body_bipedal_tailless', 'body_four_wings',
       'body_head_arms', 'body_head_base', 'body_head_legs', 'body_head_only',
       'body_insectoid', 'body_multiple_bodies', 'body_quadruped',
       'body_serpentine_body', 'body_several_limbs', 'body_two_wings',
       'body_with_fins'],
      dtype='object')


df.shape

(721, 52)

X = df.drop('legend',axis=1)
y = df['legend']

X.shape,y.shape # ((721, 51), (721,))


from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report,confusion_matrix


X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=0.80, test_size=0.20, 
                              stratify=y)
X_train, X_val, y_train, y_val = train_test_split(X, y,  stratify=y,test_size=0.20)


#  Logistic model

from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScale

scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_val_scaled = scaler.transform(X_val)

X_train_scaled
X_train_scaled.T[0].mean(), X_train_scaled.T[0].std()

model = LogisticRegression(random_state=1)
model.fit(X_train_scaled, y_train)

from sklearn.metrics import accuracy_score

y_pred = model.predict(X_val_scaled)
accuracy_score(y_val, y_pred) # 0.9310344827586207

X_test_scaled = scaler.transform(X_test)
y_pred_test = model.predict(X_test_scaled)
accuracy_score(y_test, y_pred_test) # 0.9448275862068966

# RandomForest model

from sklearn.ensemble import RandomForestClassifier
from sklearn.pipeline import make_pipeline

rfc = make_pipeline(RandomForestClassifier(criterion = 'entropy',n_jobs=-1, random_state=2,n_estimators=200))
rfc.fit(X_train, y_train)

print('test accuracy', rfc.score(X_test, y_test)) # 0.9379

# PDP , SHAP

import matplotlib.pyplot as plt
plt.rcParams['figure.dpi'] = 80
from pdpbox.pdp import pdp_isolate, pdp_plot
import shap
import numpy as np

feature = 'bug' 
isolated = pdp_isolate(
    model=model, 
    dataset=X_train, 
    model_features=X_train.columns, 
    feature=feature
);

ValueError：意外的输入维度 59，预期为 51

ValueError：模型的特征数量必须与输入匹配。模型 n_features 为 51，输入 n_features 为 59

这两种类型的错误就出现了。

我之所以写，是因为即使搜索 Stack Overflow，我也无法理解我做错了什么。

feature = " " 无论我输入什么功能，错误都会出现。

4

0 回答 0