问如何在现有的朴素贝叶斯算法中测试新数据(Python 3)

EN

import pandas as pd
import numpy as np

testdf = pd.read_csv("train_predictions.csv")

#change output settings
pd.set_option("display.width", 400)
pd.set_option("display.max_columns", 20)
pd.set_option("display.max_rows", 200)

# print data types of each column
print(testdf.dtypes)

# transform str data to numerical
from sklearn import preprocessing
le = preprocessing.LabelEncoder()
testdf["ID"] = le.fit_transform(testdf["ID"])
testdf["THAL"] = le.fit_transform(testdf["THAL"])
print(testdf.head())

# ID is not relevant to model, HEART DZ will be our target
cols = [col for col in testdf.columns if col not in    ["ID","HEART DZ"]]
data = testdf[cols]
target = testdf["HEART DZ"]
print(data.head())

from sklearn.model_selection import train_test_split
# split dataset
data_train, data_test, target_train, target_test = train_test_split(data, target, test_size=0.30, random_state=10)

# Gaussian Naive Bayes
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import accuracy_score

gnb = GaussianNB()
pred = gnb.fit(data_train, target_train).predict(data_test)
print("Naive-Bayes accuracy : ",accuracy_score(target_test, pred, normalize=True))

testdf = pd.read_csv("train_predictions.csv")
predictdf = pd.read_csv("export_dataframe.csv")

#change output settings
pd.set_option("display.width", 400)
pd.set_option("display.max_columns", 20)
pd.set_option("display.max_rows", 200)

# print data types of each column
#print(predictdf.head())

# transform str data to numerical
from sklearn import preprocessing
le = preprocessing.LabelEncoder()
testdf["ID"] = le.fit_transform(testdf["ID"])
testdf["THAL"] = le.fit_transform(testdf["THAL"])
predictdf["ID"] = le.fit_transform(predictdf["ID"])
predictdf["THAL"] = le.fit_transform(predictdf["THAL"])
#print(predictdf.head())

# ID is not relevant to model, HEART DZ will be our target (drop them)
cols = [col for col in testdf.columns if col not in ["ID","HEART DZ"]]
data = testdf[cols]
target = testdf["HEART DZ"]
pred_cols = [col for col in predictdf.columns if col not in ["ID","HEART DZ"]]
pred_data = predictdf[cols]
pred_target = predictdf["HEART DZ"]
#print(pred_data.head())

from sklearn.model_selection import train_test_split
# split dataset
data_train, data_test, target_train, target_test = train_test_split(data, target, test_size=0.30) #random_state=10)

# Gaussian Naive Bayes
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import accuracy_score

gnb = GaussianNB()
pred = gnb.fit(data_train, target_train).predict(data_test)
predictions = gnb.predict([predictdf])
#print("Naive-Bayes accuracy : ",accuracy_score(target_test, pred, normalize=True))
print(predictions)

testdf = pd.read_csv("train_predictions.csv")
testlabelsdf = pd.read_csv("train_labels.csv")
predictdf = pd.read_csv("export_dataframe.csv")
#print(testlabelsdf.head())

# transform str to int
from sklearn import preprocessing
le = preprocessing.LabelEncoder()
testdf["ID"] = le.fit_transform(testdf["ID"])
predictdf["ID"] = le.fit_transform(predictdf["ID"])
testdf["THAL"] = le.fit_transform(testdf["THAL"])
predictdf["THAL"] = le.fit_transform(predictdf["THAL"])

# ID is not relevant to model, HEART DZ will be our target (drop them)
cols = [col for col in testdf.columns if col not in ["ID"]]
data = testdf[cols]
target = testlabelsdf["HEART DZ"]

from sklearn.model_selection import train_test_split
# split dataset
data_train, data_test, target_train, target_test = train_test_split(data, target, random_state=10) #test_size=0.30,random_state=10)

# Gaussian Naive Bayes
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import accuracy_score

gnb = GaussianNB()
gnb.fit(data_train, target_train)
target_pred = gnb.predict(data_test)
ac = accuracy_score(target_test, target_pred, normalize=True)

yNew = gnb.predict(predictdf)
#print(yNew)

for i in range(len(predictdf)):
    print("Predicted: ", yNew[i])