mnist数据集怎么用(mnist数据集是怎么做出来的)

import pandas as pd
import numpy as np
from numpy import mean
from numpy import std
from sklearn.datasets import make_classification
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import RepeatedStratifiedKFold
from sklearn.linear_model import LogisticRegression

data_wide = pd.read_csv("./data/mode_wide.csv", index_col=0) #index_col=0 第一行为列名
data_wide

453 rows × 9 columns

y= 1(选car)；

y = 2 (carpool);

y = 3 (rail);

y = 4 (bus);

def choice_to_y(choice):
    if choice == 'car':
        return 1
    elif choice == 'carpool':
        return 2
    elif choice == 'rail':
        return 3
    else:
        return 4

data_wide['y'] = data_wide['choice'].map(choice_to_y)
data_wide

453 rows × 10 columns

data_wide.columns

Index(['choice', 'cost.car', 'cost.carpool', 'cost.bus', 'cost.rail',
       'time.car', 'time.carpool', 'time.bus', 'time.rail', 'y'],
      dtype='object')

X = data_wide[['cost.car', 'cost.carpool', 'cost.bus', 'cost.rail','time.car', 'time.carpool', 'time.bus', 'time.rail']]
y = data_wide['y']

model = LogisticRegression(multi_class='multinomial', solver='lbfgs')

# define the model evaluation procedure （定义模型评估程序） n_splits 就是K-flods中的K值；n_repeats是交叉验证的次数
cv = RepeatedStratifiedKFold(n_splits=10, n_repeats=3, random_state=1)
# evaluate the model and collect the scores （评估模型并收集分数）
n_scores = cross_val_score(model, X, y, scoring='accuracy', cv=cv, n_jobs=-1)
# report the model performance 
print('Mean Accuracy: %.3f (%.3f)' % (mean(n_scores), std(n_scores)))  

Mean Accuracy: 0.665 (0.061)

model.fit(X, y)

D:ANACONDAlibsite-packagessklearnlinear_model_logistic.py:818: 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
  extra_warning_msg=_LOGISTIC_SOLVER_CONVERGENCE_MSG,





LogisticRegression(multi_class='multinomial')

#生成一组新数据
new_data = np.random.rand(8)
new_data

array([0.11880174, 0.16505872, 0.14297278, 0.50355392, 0.87629855,
       0.91189688, 0.57073101, 0.19178997])

#预测
#预测新数据的分布概率
yhat = model.predict_proba([new_data])

#输出预测结果
print('Predicted Probabilities: %s' % yhat[0])

Predicted Probabilities: [0.3749058  0.20228137 0.20380141 0.21901142]


D:ANACONDAlibsite-packagessklearnbase.py:451: UserWarning: X does not have valid feature names, but LogisticRegression was fitted with feature names
  "X does not have valid feature names, but"

上面的警告是出现了无效的特征名（列名不是正确的格式）