一些关于python预测模型和识别简单数字图片的代码

需要实现先准备两个不同xlsx文件表格（有例子）和粗大数字照片（有例子），并且加到根目录下

import pandas as pd
df = pd.read_excel('手写字体识别.xlsx')
df.head()

#提取特征变量和目标变量
X = df.drop(columns='对应数字')
y = df['对应数字']

#划分训练集和测试集
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=123) # 设置random_state使得每次划分的数据一样

from sklearn.neighbors import KNeighborsClassifier as KNN
knn=KNN(n_neighbors=4)
knn.fit(X_train,y_train)

y_pred=knn.predict(X_test.values) #报错才加'.values'
print(y_pred[0:100])

a=pd.DataFrame()
a['预测值']=list(y_pred)
a['实际值']=list(y_test)
a.head()

#用于评分
from sklearn.metrics import accuracy_score
score=accuracy_score(y_pred,y_test)
score

#也用于评分，这个是系统自带的
score=knn.score(X_test.values,y_test)
score

 实操照片

文件

代码 

 

from PIL import Image
img = Image.open('数字4.png')
img = img.resize((32,32))
img

img = img.convert('L')
img

import numpy as np
img_new=img.point(lambda x:0 if x>128 else 1)
arr = np.array(img_new)
img_new

for i in range(arr.shape[0]):
    print(arr[i])

arr_new = arr.reshape(1,-1)
arr_new

print(arr_new.shape)

answer = knn.predict(arr_new)
print(str(answer[0]))

X=[[1,0],[5,1],[6,4],[4,3],[5,2]]
y=[0,1,1,0,0]

from sklearn.neural_network import MLPClassifier
mlp = MLPClassifier()
mlp.fit(X,y)

y_pred=mlp.predict(X)
import pandas as pd
a=pd.DataFrame()
a['预测值']=list(y_pred)
a['实际值']=list(y)
a.head()

from sklearn.neural_network import MLPRegressor
X=[[1,2],[3,4],[5,6],[7,8],[9,12]]
y=[1,2,3,4,5]
model=MLPRegressor(random_state=123)
model.fit(X,y)
print(model.predict([[5,5]]))

实操照片

图片

代码

 

import pandas as pd
df = pd.read_excel('产品评价.xlsx')
df.head()

!pip install jieba  #用于下载jieba插件

import jieba
word = jieba.cut(df.iloc[0]['评论'])
result = ' '.join(word)
print(result)

words=[]
for i,row in df.iterrows():
    word = jieba.cut(row['评论'])
    result = ' '.join(word)
    words.append(result)

from sklearn.feature_extraction.text import CountVectorizer
vect = CountVectorizer()
X=vect.fit_transform(words)
X=X.toarray()
words_bag=vect.vocabulary_
print(words_bag)

len(words_bag)

import pandas as pd
pd.DataFrame(X)

pd.set_option('display.max_columns',None)
pd.set_option('display.max_rows',None)
pd.DataFrame(X)
y=df['评价']

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1)

from sklearn.neural_network import MLPClassifier
mlp = MLPClassifier()
mlp.fit(X_train,y_train)

y_pred= mlp.predict(X_test)
a=pd.DataFrame()
a['预测值']=list(y_pred)
a['实际值']=list(y_test)
a.head()

comment = input('请输入评价:')
comment = [' '.join(jieba.cut(comment))]
print(comment)
X_try=vect.transform(comment)
y_pred=mlp.predict(X_try.toarray())
print(y_pred)

实操照片

文件

代码