【发布时间】：2019-03-16 01:47:37
【问题描述】：
我对如何将朴素贝叶斯中 predict.proba 的结果转换为百分比有疑问。我已经尝试了一些但失败了。我想让结果变成 50%、100%。这是我的代码示例
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import confusion_matrix
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.preprocessing import LabelEncoder
import itertools
plt.style.use('ggplot')
class bayesNaive:
def __init__(self, dataTrainInput):
self.data = pd.read_csv(dataTrainInput, delimiter=";", encoding="latin-1")
def encoderLabel(self):
self.lb = LabelEncoder()
df = pd.DataFrame(self.data,
columns=["laboratory_registration_id", "Albumin","Asam Urat", "Basofil", "Basofil Absolut","BE", "Berat Jenis", "Besi (Fe/iron)", "Eosinofil", "Eosinofil Absolut", "Eritrosit","Ferritin", "Free T4", "Glukosa Darah 2 jam PP", "Glukosa Darah Puasa","Glukosa Darah Sewaktu", "Hb-A1c", "Hematokrit", "Hemoglobin", "Kalium (K)","Klorida (Cl)", "Kolesterol HDL", "Kolesterol LDL", "Kolesterol Total", "Kreatinin","Leukosit", "Limfosit", "Limfosit Absolut", "MCH", "MCHC", "MCV", "Monosit","Monosit Absolut", "MPV", "Natrium (Na)", "Neutrofil Absolut", "Neutrofil Segmen","O2 Saturasi", "pCO2", "PDW", "pH", "pO2", "RDW-CV", "RDW-SD", "T CO2", "TIBC","T3 Total", "T4 Total", "Trigliserida", "Trombosit", "Troponin T", "TSH", "Ureum", "Age", "Gender", "Disease"])
data1 = self.data["Bakteri"]
data2 = self.data["Bilirubin"]
data3 = self.data["Blood"]
data5 = self.data["Epitel"]
data6 = self.data["Eritrosit Urin"]
data7 = self.data["Faktor Rheumatoid (RF)"]
data8 = self.data["Glukosa"]
data9 = self.data["HBsAg"]
data10 = self.data["Kejernihan"]
data11 = self.data["Keton"]
data12 = self.data["Kristal"]
data13 = self.data["Leukosit Urin"]
data14 = self.data["Nitrit"]
data15 = self.data["Protein"]
data16 = self.data["Silinder"]
data17 = self.data["Urobilinogen"]
data18 = self.data["Warna"]
x1 = self.lb.fit_transform(data1)
x2 = self.lb.fit_transform(data2)
x3 = self.lb.fit_transform(data3)
x5 = self.lb.fit_transform(data5)
x6 = self.lb.fit_transform(data6)
x7 = self.lb.fit_transform(data7)
x8 = self.lb.fit_transform(data8)
x9 = self.lb.fit_transform(data9)
x10 = self.lb.fit_transform(data10)
x11 = self.lb.fit_transform(data11)
x12 = self.lb.fit_transform(data12)
x13 = self.lb.fit_transform(data13)
x14 = self.lb.fit_transform(data14)
x15 = self.lb.fit_transform(data15)
x16 = self.lb.fit_transform(data16)
x17 = self.lb.fit_transform(data17)
x18 = self.lb.fit_transform(data18)
df1 = pd.DataFrame(x1, columns=['Bakteri'])
df2 = pd.DataFrame(x2, columns=['Bilirubin'])
df3 = pd.DataFrame(x3, columns=['Blood'])
df5 = pd.DataFrame(x5, columns=['Epitel'])
df6 = pd.DataFrame(x6, columns=['Eritrosit Urin'])
df7 = pd.DataFrame(x7, columns=['Faktor Rheumatoid (RF)'])
df8 = pd.DataFrame(x8, columns=['Glukosa'])
df9 = pd.DataFrame(x9, columns=['HBsAg'])
df10 = pd.DataFrame(x10, columns=['Kejernihan'])
df11 = pd.DataFrame(x11, columns=['Keton'])
df12 = pd.DataFrame(x12, columns=['Kristal'])
df13 = pd.DataFrame(x13, columns=['Leukosit Urin'])
df14 = pd.DataFrame(x14, columns=['Nitrit'])
df15 = pd.DataFrame(x15, columns=['Protein'])
df16 = pd.DataFrame(x16, columns=['Silinder'])
df17 = pd.DataFrame(x17, columns=['Urobilinogen'])
df18 = pd.DataFrame(x18, columns=['Warna'])
return pd.concat([df1, df2, df3, df5, df6, df7, df8, df9, df10, df11, df12, df13, df14, df15, df16, df17, df18, df], axis=1)
def split_label(self):
res = self.encoderLabel()
X = res.iloc[:, :-1].values
Y = res['Disease'].values
return X, Y
def test_split(self):
X, Y = self.split_label()
X_train, X_test, Y_train, Y_test = train_test_split(X,Y, test_size=0.2, random_state=42)
return X_train, X_test, Y_train, Y_test
def Classify_lab(self):
try:
X_train, X_test, Y_train, Y_test = self.test_split()
# print(X_test.shape)
model = GaussianNB()
model_train = model.fit(X_train, Y_train)
model_score = model_train.score(X_test, Y_test)
accuracy = round(model_score * 100, 2)
predicted = model_train.predict(X_test)
Y_prob = model_train.predict_proba(X_test)
report=classification_report(Y_test, predicted)
conf_m = confusion_matrix(Y_test, predicted)
# "precision: tp/(tp+fp)"
# "recall: tp/(tp+fn)"
# "f1-score: (2xprecisionxrecall)/(precision+recall)"
# print(test.shape)
test.columns = ["Bakteri", "Bilirubin", "Blood", "Epitel","Eritrosit Urin","Faktor Rheumatoid (RF)", "Glukosa", "HBsAg", "Kejernihan", "Keton", "Kristal", "Leukosit Urin", "Nitrit", "Protein", "Silinder", "Urobilinogen", "Warna","laboratory_registration_id", "Albumin", "Asam Urat", "Basofil", "Basofil Absolut","BE", "Berat Jenis", "Besi (Fe/iron)", "Eosinofil", "Eosinofil Absolut", "Eritrosit","Ferritin", "Free T4", "Glukosa Darah 2 jam PP", "Glukosa Darah Puasa","Glukosa Darah Sewaktu", "Hb-A1c", "Hematokrit", "Hemoglobin", "Kalium (K)","Klorida (Cl)", "Kolesterol HDL", "Kolesterol LDL", "Kolesterol Total", "Kreatinin","Leukosit", "Limfosit", "Limfosit Absolut", "MCH", "MCHC", "MCV", "Monosit","Monosit Absolut", "MPV", "Natrium (Na)", "Neutrofil Absolut", "Neutrofil Segmen","O2 Saturasi", "pCO2", "PDW", "pH", "pO2", "RDW-CV", "RDW-SD", "T CO2", "TIBC","T3 Total", "T4 Total", "Trigliserida", "Trombosit", "Troponin T", "TSH", "Ureum","Age", "Gender"]
labels = pd.DataFrame(predicted)
# print(Y_prob)
print("bulatan")
# Y_prob[:, 1:3] = np.around(Y_prob[:,1:3],decimals=1)
probability = pd.DataFrame(Y_prob)
labels.columns = ["Disease"]
probability.columns = ["Diabetes mellitus", "Ginjal","Jantung", "Thalassemia"]
result = pd.concat([test, labels, probability], axis=1)
# Z = self.decodeLabel(X_test)
# print("Ini", Z)
# exit()
return [result, str(accuracy), report, conf_m]
except ValueError as v:
print(v)
except FileNotFoundError:
print('File not found')
if __name__ == '__main__':
dataTrainInput = "perc4.csv"
obj = bayesNaive(dataTrainInput)
print(obj.Classify_lab())
在 Classify_lab() 中，我预测其他目标的概率
Y_prob = model_train.predict_proba(X_test)
然后，我创建数据框
probability = pd.DataFrame(Y_prob)
当我运行概率时，我会得到这个结果
Diabetes mellitus ... Thalassemia
0 1.000000e+00 ... 0.000000e+00
1 5.693959e-28 ... 0.000000e+00
2 1.610343e-182 ... 0.000000e+00
3 4.347851e-04 ... 9.949097e-01
4 2.611833e-24 ... 0.000000e+00
5 6.281686e-32 ... 1.000000e+00
6 1.000000e+00 ... 3.472943e-99
7 2.580374e-132 ... 0.000000e+00
8 1.457926e-26 ... 1.000000e+00
9 1.000000e+00 ... 0.000000e+00
10 4.993317e-33 ... 1.000000e+00
如果我在 HTML 中运行概率，我会得到这个结果
非常感谢...
【问题讨论】：
标签： probability predict naivebayes