读取单值HDF5 C ++

Question

情况：

我尝试从//File Path hid_t H5_hid_RESULTS = H5Fcreate (V_FIn_HDF5_Path.absoluteFilePath().toUtf8().constData(), H5F_ACC_RDONLY, H5P_DEFAULT, H5P_DEFAULT); //Status (Error Output?) herr_t status; //read dataset "heigth" int32_t heigth[1]; hid_t H5_hid_heigth = H5Dopen1(H5_hid_RESULTS, "heigth"); status = H5Dread(H5_hid_heigth, H5T_NATIVE_INT, H5S_ALL, H5S_ALL, H5P_DEFAULT, heigth); qDebug() << "heigth" << heigth[0]; status = H5Dclose(H5_hid_heigth); //Close: file status = H5Fclose (H5_hid_RESULTS); 文件中读取一个值。

系统：

• Windows 7（64位）
• c ++（MSVC17 64bit）
• Qt Creator（5.10.1）
• HDF5（1.8.15）

我的代码：

int[1]

目标 .hdf5文件（在查看器中）：

结果：

qDebug打印一个随机数（例如104610208），而不是预期的512。

问题：

• 为什么会这样？
• 我应该更改为读取int，float等内容吗？使用2D自制数组时，它可以工作，但我需要读取的.hdf5中的单个值却不能。

我尝试过的事情：

• 我尝试使用int32_t[1]代替int：结果相同。
• 我尝试使用nt32_t[1]代替i D:\...\xyz.cpp:47: Error: C2664: "herr_t H5Dread(hid_t,hid_t,hid_t,hid_t,hid_t,void *)" : Conversion from argument 6 from "int" to "void *" not possible： int*
• 我尝试使用int32_t[1]代替0x7fe00000001：*heigth我猜想值的地址。如果我尝试打印heigth而不是"/heigth"，则在调用函数时会崩溃
• 我尝试了其他格式并进行了投射，但没有付出任何努力。
• 我尝试通过"heigth"而不是import pandas as pd import numpy as np import random from sklearn.model_selection import train_test_split from sklearn.feature_extraction.text import CountVectorizer from sklearn.svm import LinearSVC from sklearn.naive_bayes import MultinomialNB from sklearn import linear_model from sklearn.metrics import accuracy_score from sklearn.pipeline import Pipeline, FeatureUnion from sklearn.base import BaseEstimator, TransformerMixin from sklearn.model_selection import GridSearchCV # Based on the following which has more examples: # http://nbviewer.jupyter.org/github/michelleful/SingaporeRoadnameOrigins/blob/master/notebooks/04%20Adding%20features%20with%20Pipelines.ipynb # http://michelleful.github.io/code-blog//2015/06/18/classifying-roads/ # http://zacstewart.com/2014/08/05/pipelines-of-featureunions-of-pipelines.html # https://stackoverflow.com/questions/49466193/how-to-add-a-feature-to-a-vectorized-data-set/49501769#49501769 # Load ANSI file into pandas dataframe. df = pd.read_csv(r'e:/work/python/papf.txt', encoding = 'latin1', usecols=['LAST_NAME', 'RACE']) # Convert last name to lower case. df['LAST_NAME'] = df['LAST_NAME'].str.lower() # Remove the last name spaces. # df['LAST_NAME'] = df['LAST_NAME'].str.replace(' ', '') # Remove all rows where race is NOT in African, Coloured, White, Indian. df = df.drop(df[~df['RACE'].isin(['African', 'Coloured', 'White', 'Indian'])].index) # Returns a column from the dataframe named df as a numpy array of type string. class TextExtractor(BaseEstimator, TransformerMixin): """Adapted from code by @zacstewart https://github.com/zacstewart/kaggle_seeclickfix/blob/master/estimator.py Also see Zac Stewart's excellent blogpost on pipelines: http://zacstewart.com/2014/08/05/pipelines-of-featureunions-of-pipelines.html """ def __init__(self, column_name): self.column_name = column_name def transform(self, df): # Select the relevant column and return it as a numpy array. # Set the array type to be string. return np.asarray(df[self.column_name]).astype(str) # This refers to the df passed as a parameter, and not to the global scope one. def fit(self, *_): return self class Apply(BaseEstimator, TransformerMixin): """Takes in a function and applies it element-wise to every element in the numpy array it's supplied with.""" def __init__(self, fn): self.fn = np.vectorize(fn) def transform(self, data): # Note: reshaping is necessary because otherwise sklearn # interprets the 1-d array as a single sample. return self.fn(data.reshape(data.size, 1)) def fit(self, *_): return self class AverageWordLengthExtractor(BaseEstimator, TransformerMixin): """Takes in dataframe, extracts last name column, outputs average word length""" def __init__(self): pass def average_word_length(self, name): """Helper code to compute average word length of a name""" return np.mean([len(word) for word in name.split()]) def transform(self, df, y=None): """The workhorse of this feature extractor""" return df['LAST_NAME'].apply(self.average_word_length) # This refers to the df passed as a parameter, and not to the global scope one. def fit(self, df, y=None): """Returns self unless something different happens in train and test""" return self # Let's pick the same random 10% of the data to train with. random.seed(1965) train_test_set = df.loc[random.sample(list(df.index.values), int(len(df) / 10))] # X = train_test_set[['road_name', 'has_malay_road_tag']] X = train_test_set[['LAST_NAME']] y = train_test_set['RACE'] vect = CountVectorizer(ngram_range=(1,4), analyzer='char') clf = LinearSVC() # #MultinomialNB() #linear_model.SGDClassifier(max_iter=500) pipeline = Pipeline([ ('name_extractor', TextExtractor('LAST_NAME')), # Extract names from df. ('text_features', FeatureUnion([ ('vect', vect), # Extract ngrams from names. ('num_words', Apply(lambda s: len(s.split()))), # Number of words. ('ave_word_length', Apply(lambda s: np.mean([len(w) for w in s.split()]))), # Average word length. ])), ('clf' , clf), # Feed the output through a classifier. ]) def run_experiment(X, y, pipeline, num_expts=100): scores = list() for i in range(num_expts): X_train, X_test, y_train, y_true = train_test_split(X, y) model = pipeline.fit(X_train, y_train) # Train the classifier. y_test = model.predict(X_test) # Apply the model to the test data. #print(X_test) #print(type(X_test)) score = accuracy_score(y_test, y_true) # Compare the results to the gold standard. scores.append(score) print(sum(scores) / num_expts) # Run x times (num_expts) and get the average accuracy. run_experiment(X, y, pipeline, 1) # Train a final model for use in the actual output. X_train, X_test, y_train, y_true = train_test_split(X, y) model = pipeline.fit(X_train, y_train) # Train the classifier. df2 = pd.DataFrame(columns=['LAST_NAME'], data=[['Joemat']]) # Create a test case of one. print(model.predict(df2)) # Solution to this part might be here: https://stackoverflow.com/questions/49466193/how-to-add-a-feature-to-a-vectorized-data-set/49501769#49501769 pg = {'clf__C': [0.1, 1, 10, 100]} grid = GridSearchCV(pipeline, param_grid=pg, cv=5) X_train, X_test, y_train, y_true = train_test_split(X, y) grid.fit(X_train, y_train) print(grid.best_params_) # {'clf__C': 0.1} print(grid.best_score_) # 0.702290076336 ：相同的结果。

Answer 1

如文件查看器所示，您的数据类型512为H5T_NATIVE_INT32，而不是H5T_NATIVE_INT。换句话说，您尝试读取只有32位整数的64位整数。这应该为您工作：

status = H5Dread(H5_hid_heigth, H5T_NATIVE_INT32, 
                 H5S_ALL, H5S_ALL, H5P_DEFAULT, heigth);

Answer 2

我受此example的启发，使用完全不同但非常简单的方法解决了这个问题。基本上与链接中的代码相同，但经过了极大简化，因此使用c ++和HDF5的新手可以理解它：

//open file (My path is zensored, project from work)
const H5std_string  H5_Path_Results("C:/.../results.hdf5");
H5File              H5_File_Results(H5_Path_Results, H5F_ACC_RDONLY);

//open set
const H5std_string  H5_Nam_Height("height");
DataSet             H5_Set_Height = H5_File_Results.openDataSet(H5_Nam_Height);

//read set
int                 height[1];
H5_Set_Height.read(height, PredType::NATIVE_INT, H5S_ALL, H5S_ALL);
qDebug() << height[0];

//close set
H5_Set_Height.close();

//close file
H5_File_Results.close();

这给出了我想读取的512输出。

当然需要#include <hdf5.h>和#include <H5Cpp.h>，必须将库添加到项目中，并且.hdf5文件必须存在。