小编Viv*_*mar的帖子

我在Ubuntu 14上工作.我安装了python3和pip3.当我尝试使用pip3时,我有这个错误

Traceback (most recent call last):
  File "/usr/local/bin/pip3", line 6, in <module>
    from pkg_resources import load_entry_point
  File "/usr/local/lib/python3.5/dist-packages/pkg_resources/__init__.py", line 70, i
n <module>
    import packaging.version
ImportError: No module named 'packaging'

有人知道这是什么问题吗？

非常感谢

我有一个要求，需要将数据帧列的行转换为列，但是在 GROUPBY 之后我遇到了问题。下面是一组 3 个用户，其类型可以在 type1 到 type6 之间。

user_id1    type4
user_id1    type6
user_id1    type1
user_id1    type2
user_id1    type1
user_id1    type6
user_id2    type1
user_id2    type2
user_id2    type2
user_id2    type1
user_id2    type3
user_id2    type4
user_id2    type5
user_id2    type6
user_id2    type2
user_id2    type6
user_id3    type1
user_id3    type2
user_id3    type3
user_id3    type2

我期望的输出是 -

user_id   type1 type2   type3   type4   type5   type6
user_id1    2    1       0       1       0       2
user_id2    2    3       1       1       1       2
user_id3    1    2       1       0       0       0

我尝试对类型进行 …

sklearn在我的计算机上已经工作半年了，我已经停止使用它了，现在却没有。我在program.py中的import语句遇到问题：

from sklearn import tree

看起来真的很乱：

Traceback (most recent call last):   File "E:/DecisionModel.py", line 1, in <module>
    from sklearn import tree   File "C:\Users\AppData\Local\Programs\Python\Python35\lib\site-packages\sklearn\__init__.py", line 57, in <module>
    from .base import clone   File "C:\Users\AppData\Local\Programs\Python\Python35\lib\site-packages\sklearn\base.py", line 12, in <module>
    from .utils.fixes import signature   File "C:\Users\AppData\Local\Programs\Python\Python35\lib\site-packages\sklearn\utils\__init__.py", line 11, in <module>
    from .validation import (as_float_array,   File "C:\Users\AppData\Local\Programs\Python\Python35\lib\site-packages\sklearn\utils\validation.py", line 18, in <module>
    from ..utils.fixes import signature   File "C:\Users\AppData\Local\Programs\Python\Python35\lib\site-packages\sklearn\utils\fixes.py", line 403, in <module>
    from scipy.stats import rankdata   File "C:\Users\AppData\Local\Programs\Python\Python35\lib\site-packages\scipy\stats\__init__.py", line 344, in <module>
    from .stats import …

我正在尝试使用 R（版本 3.3.3）和 h2o 中的深度学习（版本 3.10.5.1）构建堆叠集成模型来预测商家流失。响应变量是二进制的。目前，我正在尝试运行代码以使用网格搜索开发的前 5 个模型构建堆叠集成模型。但是，当代码运行时，我得到 java.lang.NullPointerException 错误，输出如下：

java.lang.NullPointerException
    at hex.StackedEnsembleModel.checkAndInheritModelProperties(StackedEnsembleModel.java:265)
    at hex.ensemble.StackedEnsemble$StackedEnsembleDriver.computeImpl(StackedEnsemble.java:115)
    at hex.ModelBuilder$Driver.compute2(ModelBuilder.java:173)
    at water.H2O$H2OCountedCompleter.compute(H2O.java:1349)
    at jsr166y.CountedCompleter.exec(CountedCompleter.java:468)
    at jsr166y.ForkJoinTask.doExec(ForkJoinTask.java:263)
    at jsr166y.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:974)
    at jsr166y.ForkJoinPool.runWorker(ForkJoinPool.java:1477)
    at jsr166y.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:104)

下面是我用来进行超参数网格搜索和构建集成模型的代码：

hyper_params <- list(
                  activation=c("Rectifier","Tanh","Maxout","RectifierWithDropout","TanhWithDropout","MaxoutWithDropout"),
                  hidden=list(c(50,50),c(30,30,30),c(32,32,32,32,32),c(64,64,64,64,64),c(100,100,100,100,100)),
                  input_dropout_ratio=seq(0,0.2,0.05),
                  l1=seq(0,1e-4,1e-6),
                  l2=seq(0,1e-4,1e-6),
                  rho = c(0.9,0.95,0.99,0.999),
                  epsilon=c(1e-10,1e-09,1e-08,1e-07,1e-06,1e-05,1e-04)
                )

search_criteria <- list(
                      strategy = "RandomDiscrete",
                      max_runtime_secs = 3600,
                      max_models = 100,
                      seed=1234,
                      stopping_metric="misclassification",      
                      stopping_tolerance=0.01,                  
                      stopping_rounds=5
                    )

dl_ensemble_grid <- h2o.grid(
                          hyper_params = hyper_params,
                          search_criteria = search_criteria,
                          algorithm="deeplearning",
                          grid_id = "final_grid_ensemble_dl",
                          x=predictors,
                          y=response,
                          training_frame = h2o.rbind(train, valid, test), …

我正在努力从我的RandomForestRegressor中提取功能的重要性，我得到了：

AttributeError：“ GridSearchCV”对象没有属性“ feature_importances_”。

有人知道为什么没有属性吗？根据文档，应该存在此属性？

完整代码：

from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import GridSearchCV

#Running a RandomForestRegressor GridSearchCV to tune the model.
parameter_candidates = {
    'n_estimators' : [650, 700, 750, 800],
    'min_samples_leaf' : [1, 2, 3],
    'max_depth' : [10, 11, 12],
    'min_samples_split' : [2, 3, 4, 5, 6]
}

RFR_regr = RandomForestRegressor()
CV_RFR_regr = GridSearchCV(estimator=RFR_regr, param_grid=parameter_candidates, n_jobs=5, verbose=2)
CV_RFR_regr.fit(X_train, y_train)

#Predict with testing set
y_pred = CV_RFR_regr.predict(X_test)

#Extract feature importances
importances = CV_RFR_regr.feature_importances_

我使用 sklearn 应用带有 K-fold 的决策树，有人可以帮助我显示它的平均分数。下面是我的代码：

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import KFold
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import confusion_matrix,classification_report

dta=pd.read_csv("https://archive.ics.uci.edu/ml/machine-learning-databases/blood-transfusion/transfusion.data")

X=dta.drop("whether he/she donated blood in March 2007",axis=1)

X=X.values # convert dataframe to numpy array

y=dta["whether he/she donated blood in March 2007"]

y=y.values # convert dataframe to numpy array

kf = KFold(n_splits=10)

KFold(n_splits=10, random_state=None, shuffle=False)

clf_tree=DecisionTreeClassifier()

for train_index, test_index in kf.split(X):
    X_train, X_test = X[train_index], X[test_index]
    y_train, y_test = y[train_index], y[test_index] …

对来自 Keras 模型的 Multiclass 输出使用自定义评分会为 cross_val_score 或 GridSearchCV 返回相同的错误，如下所示（它在 Iris 上，因此您可以直接运行它进行测试）：

import numpy as np
from sklearn import datasets
from sklearn.model_selection import train_test_split, cross_val_score, GridSearchCV
from keras.models import Sequential
from keras.layers import Dense
from keras.utils import to_categorical
from keras.wrappers.scikit_learn import KerasClassifier

iris = datasets.load_iris()
X= iris.data
Y = to_categorical(iris.target)

X_train, X_test, Y_train, Y_test = train_test_split(X, Y, train_size=0.8, random_state=1000)

def create_model(optimizer='rmsprop'):
    model = Sequential()
    model.add(Dense(8,activation='relu',input_shape = (4,)))
    model.add(Dense(3,activation='softmax'))
    model.compile(optimizer = optimizer,
                  loss='categorical_crossentropy',
                  metrics=['accuracy'])
    return model


model = KerasClassifier(build_fn=create_model,
                        epochs=10, 
                        batch_size=5,
                        verbose=0) …

假设我们有一个 Pandas 数据框和一个 scikit-learn 模型，并使用该数据框进行训练（拟合）。有没有办法进行逐行预测？用例是使用 sklearn 模型使用预测函数填充数据框中的空值。

我预计这可以使用 pandas apply 函数（轴=1）实现，但我不断收到维度错误。

使用 Pandas 版本“0.22.0”和 sklearn 版本“0.19.1”。

简单的例子：

import pandas as pd
from sklearn.cluster import kmeans

data = [[x,y,x*y] for x in range(1,10) for y in range(10,15)]

df = pd.DataFrame(data,columns=['input1','input2','output'])

model = kmeans()
model.fit(df[['input1','input2']],df['output'])

df['predictions'] = df[['input1','input2']].apply(model.predict,axis=1)

由此产生的维数误差：

ValueError: ('Expected 2D array, got 1D array instead:\narray=[ 1. 
10.].\nReshape 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.', 
'occurred …

问题：

在训练过程中，我的模型的性能看起来相当不错。然而，sklearn 的classification_report 的结果几乎所有地方的精度、召回率和 f1 都为零。我做错了什么导致训练性能和推理之间如此不匹配？（我使用 Keras 和 TensorFlow 后端。）

我的代码：

我使用valiation_split参数生成两个生成器（训练、验证），如下所示：

train_datagen = ImageDataGenerator(
rescale=1. / 255, validation_split=0.15)

train_generator = train_datagen.flow_from_directory(
train_data_dir,
target_size=(img_height, img_width),
batch_size=batch_size,
class_mode='categorical', subset="training")

validation_generator = train_datagen.flow_from_directory(
train_data_dir,
target_size=(img_height, img_width),
batch_size=batch_size,
class_mode='categorical', subset="validation", shuffle=False)

我shuffle=False在validation_generator中进行设置，以确保它不会混合图像和标签的关系以供稍后的评估。

接下来，我像这样训练我的模型：

history = model.fit_generator(
    train_generator,
    steps_per_epoch=nb_train_samples // batch_size,
    epochs=epochs,
    validation_data=validation_generator,
    validation_steps=nb_validation_samples // batch_size,
    verbose=1)

性能还可以：

Epoch 1/5
187/187 [==============================] - 44s 233ms/step - loss: 0.7835 - acc: 0.6744 - val_loss: 1.2918 - val_acc: 0.6079
Epoch 2/5
187/187 …

我想使用sklearn的MLPClassifier

mlp = MLPClassifier(hidden_layer_sizes=(50,), max_iter=10, alpha=1e-4,
                solver='sgd', verbose=10, tol=1e-4, random_state=1,
                learning_rate_init=.1)

我没有找到损失函数的任何参数，我希望它是mean_squared_error。是否可以根据模型来确定？