python - 用于动物分类的 Sklearn 模型

Question

编辑:所以我设法用所有建议修复了错误。但现在 model.predict 部分给了我这个问题。

Expected 2D array, got 1D array instead:
array=[   12 15432    40    20    33 40000 12800    20 19841     0     0].
Reshape your data either using array.reshape(-1, 1) if your data has a 
single feature or array.reshape(1, -1) if it contains a single sample.

这是我正在使用的新代码

'''
This method is to handel the training and testing of the models
'''
def testTrainModel(model, xTrain, yTrain, xTest, yTest):
    print("Start Method")
    print("Traing Model")
    model.fit(xTrain, yTrain)
    print("Model Trained")
    print("testing models")
    results = model.predict(xTest)

    print(model.__class__," Prediction Report")
    print(classification_report(results,yTest))
    print("Confusion Matrix")
    print(confusion_matrix(results,yTest))
    print("Accuracy is ", accuracy_score(results, yTest)*100)
    lables =["Hunter", "Scavenger"]
    plotConfusionMatrix(confusion_matrix(results,yTest),
                    lables,
                     title='Confusion matrix')

#Data set Preprocess data
dataframe = pd.read_csv("animalData.csv", dtype = 'category')
print(dataframe.head())
dataframe = dataframe.drop(["Name"], axis = 1)
cleanup = {"Class": {"Primary Hunter" : 0, "Primary Scavenger": 1 }}
dataframe.replace(cleanup, inplace = True)
print(dataframe.head())

#array = dataframe.values
#Data splt
# Seperating the data into dependent and independent variables
X = dataframe.iloc[:, :-1].values
y = dataframe.iloc[:,-1].values
#Get training and testoing data

#Set up the models Put model nicknake and model
models = []
models.append(('LogReg', LogisticRegression()))
models.append(('LDA', LinearDiscriminantAnalysis()))
models.append(('KNN', KNeighborsClassifier()))
models.append(('DecTree', DecisionTreeClassifier()))
models.append(('NB', GaussianNB()))
models.append(('SVM', SVC()))

#Create all the models
logReg = LogisticRegression()
lda = LinearDiscriminantAnalysis()
knn = KNeighborsClassifier()
decsTree = DecisionTreeClassifier()
nb = GaussianNB()
svm = SVC()

#Test value
trex = [12,15432,40,20,33,40000,12800,20,19841,0,0,0]
testTrainModel(logReg,X, y, trex[:-1], trex[-1:])
testTrainModel(lda,X, y, trex[:-1], trex[-1:])
testTrainModel(knn,X, y, trex[:-1], trex[-1:])
testTrainModel(decsTree,X, y, trex[:-1], trex[-1:])
testTrainModel(nb,X, y, trex[:-1], trex[-1:])
testTrainModel(svm,X, y, trex[:-1], trex[-1:])

旧版:我在这里想做的是使用一系列动物特征，例如 dentry 和大小，然后使用一些内置模型，例如 SVN KNN 等以及我制作的 cvs 数据集。但它一直说它不能将字符串转换为 float ，当我取出简历中的所有字符串时，它确实有效，但我不知道这是否是我想要的，因为我想将每个动物绘制为猎人或清道夫。我真的不知道我在这里做错了什么，因为我是Python新手。也许有人可以帮助解决这个问题并查看我的代码并告诉我我在这里做错了什么。任何改进这一点的建议也将被愉快地接受。

所以我的代码如下所示:

import pandas as pd
import numpy as np
import itertools
import matplotlib.pyplot as plt
from sklearn import model_selection
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report


def plotConfusionMatrix(cm, classes,
                      normalize=False,
                      title='Confusion matrix',
                      cmap=plt.cm.Blues):

plt.imshow(cm, interpolation='nearest', cmap=cmap)
plt.title(title)
plt.colorbar()
tick_marks = np.arange(len(classes))
plt.xticks(tick_marks, classes, rotation=45)
plt.yticks(tick_marks, classes)

fmt = '.2f' if normalize else 'd'
thresh = cm.max() / 2.
for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
    plt.text(j, i, format(cm[i, j], fmt),
             horizontalalignment="center",
             color="white" if cm[i, j] > thresh else "black")

plt.tight_layout()
plt.ylabel('True label')
plt.xlabel('Predicted label')
plt.show()

'''
This method is to handel the training and testing of the models
'''
def testTrainModel(model, xTrain, yTrain, xTest, yTest):
    print("Start Method")
    print("Traing Model")
    model.fit(xTrain, yTrain)
    print("Model Trained")
    print("testing models")
    results = model.predict(xTest)

    print(model.__class__," Prediction Report")
    print(classification_report(results,yTest))
    print("Confusion Matrix")
    print(confusion_matrix(results,yTest))
    print("Accuracy is ", accuracy_score(results, yTest)*100)
    lables =["Hunter", "Scavenger"]
    plotConfusionMatrix(confusion_matrix(results,yTest),
                        lables,
                         title='Confusion matrix')




#T-Rex, 12, 15432,  40, 20, 33, 40000,  12800,  20, 19841,  0,  0,


#Data set
dataframe = pd.read_csv("animalData.csv")
print(dataframe.head())
#array = dataframe.values
#Data splt
# Seperating the data into dependent and independent variables
X = dataframe.iloc[:, :-1].values
y = dataframe.iloc[:,-1].values
#Get training and testoing data

seed = 7 #prepare configuration for cross validation test harness

#Set up the models Put model nicknake and model
models = []
models.append(('LogReg', LogisticRegression()))
models.append(('LDA', LinearDiscriminantAnalysis()))
models.append(('KNN', KNeighborsClassifier()))
models.append(('DecTree', DecisionTreeClassifier()))
models.append(('NB', GaussianNB()))
models.append(('SVM', SVC()))


#store the results
results = []
names =[]
scoring = 'accuracy'
#print the results

for name, model in models:
    kfold = model_selection.KFold(n_splits=9, random_state=seed)
    cv_results = model_selection.cross_val_score(model, X, y, cv=kfold,             scoring=scoring)
    results.append(cv_results)
    names.append(name)
    msg = "Model:%s:\n Cross Validation Score Mean:%f - StdDiv:(%f)" % (name, cv_results.mean(), cv_results.std())
    print(msg)

#plot the data
figure1 = plt.figure()
figure1.suptitle("Algorithm Comparision")
ax = figure1.add_subplot(111)
plt.boxplot(results)
ax.set_xticklabels(names)
plt.show()

#Create all the models
logReg = LogisticRegression()
lda = LinearDiscriminantAnalysis()
knn = KNeighborsClassifier()
decsTree = DecisionTreeClassifier()
nb = GaussianNB()
svm = SVC()

#Test value
trex = ["T-Rex",12,15432,40,20,33,40000,12800,20,19841,0,0,"Primary Hunter"]
testTrainModel(logReg,X, y, trex[:-1], trex[-1:])
testTrainModel(lda,X, y, trex[:-1], trex[-1:])
testTrainModel(knn,X, y, trex[:-1], trex[-1:])
testTrainModel(decsTree,X, y, trex[:-1], trex[-1:])
testTrainModel(nb,X, y, trex[:-1], trex[-1:])
testTrainModel(svm,X, y, trex[:-1], trex[-1:])

现在这已经做了很多事情，我认为我一切都正确，但可能我的数据也是错误的。

这是测试 csv 文件

Name,teethLength,weight,length,hieght,speed,Calorie Intake,Bite Force,Prey Speed,PreySize,EyeSight,Smell,Class Crocodile,4,2400,23,1.6,8,2500,3700,30,881,0,0,Primary Hunter Lion,2.7,416,9.8,3.9,50,7236,650,35,1300,0,0,Primary Hunter Bear,3.6,600,7,3.35,40,20000,975,0,0,0,0,Primary Scavenger Tiger,3,260,12,3,40,7236,1050,37,160,0,0,Primary Hunter Hyena,0.27,160,5,2,37,5000,1100,20,40,0,0,Primary Scavenger Jaguar,2,220,5.5,2.5,40,5000,1350,15,300,0,0,Primary Hunter Cheetah,1.5,154,4.9,2.9,70,2200,475,56,185,0,0,Primary Hunter KomodoDragon,0.4,150,8.5,1,13,1994,240,24,110,0,0,Primary Scavenger

对此的任何帮助将不胜感激。

堆栈跟踪

  File "<ipython-input-10-691557e6b9ae>", line 1, in <module>
runfile('E:/TestPythonCode/Classifier.py', wdir='E:/TestPythonCode')

  File "C:\Users\matth\Anaconda3\envs\TensorfGPU2\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 678, in runfile
execfile(filename, namespace)

  File "C:\Users\matth\Anaconda3\envs\TensorfGPU2\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 106, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)

  File "E:/TestPythonCode/Classifier.py", line 110, in <module>
cv_results = model_selection.cross_val_score(model, X, y, cv=kfold, scoring=scoring)

  File "C:\Users\matth\Anaconda3\envs\TensorfGPU2\lib\site-packages\sklearn\model_selection\_validation.py", line 342, in cross_val_score
pre_dispatch=pre_dispatch)

  File "C:\Users\matth\Anaconda3\envs\TensorfGPU2\lib\site-packages\sklearn\model_selection\_validation.py", line 206, in cross_validate
for train, test in cv.split(X, y, groups))

  File "C:\Users\matth\Anaconda3\envs\TensorfGPU2\lib\site-packages\sklearn\externals\joblib\parallel.py", line 779, in __call__
while self.dispatch_one_batch(iterator):

  File "C:\Users\matth\Anaconda3\envs\TensorfGPU2\lib\site-packages\sklearn\externals\joblib\parallel.py", line 625, in dispatch_one_batch
self._dispatch(tasks)

  File "C:\Users\matth\Anaconda3\envs\TensorfGPU2\lib\site-packages\sklearn\externals\joblib\parallel.py", line 588, in _dispatch
job = self._backend.apply_async(batch, callback=cb)

  File "C:\Users\matth\Anaconda3\envs\TensorfGPU2\lib\site-packages\sklearn\externals\joblib\_parallel_backends.py", line 111, in apply_async
result = ImmediateResult(func)

  File "C:\Users\matth\Anaconda3\envs\TensorfGPU2\lib\site-packages\sklearn\externals\joblib\_parallel_backends.py", line 332, in __init__
self.results = batch()

  File "C:\Users\matth\Anaconda3\envs\TensorfGPU2\lib\site-packages\sklearn\externals\joblib\parallel.py", line 131, in __call__
return [func(*args, **kwargs) for func, args, kwargs in self.items]

  File "C:\Users\matth\Anaconda3\envs\TensorfGPU2\lib\site-packages\sklearn\externals\joblib\parallel.py", line 131, in <listcomp>
return [func(*args, **kwargs) for func, args, kwargs in self.items]

  File "C:\Users\matth\Anaconda3\envs\TensorfGPU2\lib\site-packages\sklearn\model_selection\_validation.py", line 458, in _fit_and_score
estimator.fit(X_train, y_train, **fit_params)

  File "C:\Users\matth\Anaconda3\envs\TensorfGPU2\lib\site-packages\sklearn\linear_model\logistic.py", line 1216, in fit
    order="C")

  File "C:\Users\matth\Anaconda3\envs\TensorfGPU2\lib\site-packages\sklearn\utils\validation.py", line 573, in check_X_y
    ensure_min_features, warn_on_dtype, estimator)

  File "C:\Users\matth\Anaconda3\envs\TensorfGPU2\lib\site-    packages\sklearn\utils\validation.py", line 433, in check_array
    array = np.array(array, dtype=dtype, order=order, copy=copy)

ValueError: could not convert string to float: 'KomodoDragon'

Answer 1

如果使用numpy.ndarry，则字符串元素和浮点元素一起使用是无效的。例如:原生 Python 列表:

mylist = [1, 3, 'KomodoDragon']

没关系，但是当您尝试将 list mylist 转换为 ndarry 对象时，例如:

mylist = np.array(mylist, dtype=float)

会发生错误

could not convert string to float: 'KomodoDragon'

。您可以使用one-hot编码来处理这个问题。