I want to know if it is possible to import data of attitude and position (roll/pitch/yaw & xyz) from a comma separated file to Blender?
I recorded data from a little RC car and I want to represent its movement in a 3D world.
I have timestamps too, so if there's a way to animated the movement of the object it'll be superb!!
Any help will be greatly appreciated!!
Best Regards.
A slight modifcation, making use of the csv module
import bpy
import csv
position_vectors = []
filepath = "C:\\Work\\position.log"
csvfile = open(filepath, 'r', newline='')
ofile = csv.reader(csvfile, delimiter=',')
for row in ofile:
position_vectors.append(tuple([float(i) for i in row]))
csvfile.close()
This will get your points into Blender. Note the delimiter parameter in csv.reader, change that accordingly. With a real example file of your RC car we could provide a more complete solution.
For blender v2.62:
If you have a file "positions.log" looking like:
-8.691985196313894e-002; 4.119284642631801e-001; -5.832147659661263e-001
1.037146774956164e+000; 8.137243553005405e-002; -5.703274929662892e-001
-3.602584527944123e-001; 8.378614512537046e-001; 2.615265921163826e-001
6.266465707681335e-001; -1.128416901202341e+000; -1.664644365541639e+000
3.327523280880091e-001; 4.488553740582839e-001; -2.449449085462368e+000
-7.311567199869298e-001; -1.860587923723032e+000; -1.297179602213110e+000
-7.453603745688361e-003; 4.770473577895327e-001; -2.319515785100494e+000
1.935170866863264e-001; -2.010280476717868e+000; 3.748000986190077e-001
5.201529166915653e-001; 3.952972788761738e-001; 1.658581747430548e+000
4.719198263774027e-001; 1.526020825619557e+000; 3.187088567866725e-002
you can read it with this python script in blender (watch out for the indentation!)
import bpy
from mathutils import *
from math import *
from bpy.props import *
import os
import time
# Init
position_vector = []
# Open file
file = open("C:\\Work\\position.log", "r")
# Loop over line in file
for line in file:
# Split line at ";"
splittet_line = line.split(";")
# Append new postion
position_vector.append(
Vector((float(splittet_line[0]),
float(splittet_line[1]),
float(splittet_line[2]))))
# Close file
file.close()
# Get first selected object
selected_object = bpy.context.selected_objects[0]
# Get first selected object
for position in position_vector:
selected_object.location = position
This reads the file and updates the position of the first selected object accordingly. Way forward: What you have to find out is how to set the keyframes for the animation...
Consider this python snippet to add to the solutions above
obj = bpy.context.object
temporalScale=bpy.context.scene.render.fps
for lrt in locRotArray:
obj.location = (lrt[0], lrt[1], lrt[2])
# radians, and do you want XYZ, or ZYX?
obj.rotation_euler = (lrt[3], lrt[4], lrt[5])
time = lrt[6]*temporalScale
obj.keyframe_insert(data_path="location", frame=time)
obj.keyframe_insert(data_path="rotation_euler", frame=time)
I haven't tested it, but it will probably work, and gets you started.
With a spice2xyzv file as input file. The script writed by "Mutant Bob" seems to work.
But the xyz velocity data are km/s not euler angles, I think, and the import does not work for the angles.
# Records are <jd> <x> <y> <z> <vel x> <vel y> <vel z>
# Time is a TDB Julian date
# Position in km
# Velocity in km/sec
2456921.49775 213928288.518 -446198013.001 -55595492.9135 6.9011736 15.130842 0.54325805
Is there a solution to get them in Blender? Should I convert velocity angle to euler, is that possible in fact?
I use this script :
import bpy
from mathutils import *
from math import *
from bpy.props import *
import os
import time
# Init
position_vector = []
# Open file
file = open("D:\\spice2xyzv\\export.xyzv", "r")
obj = bpy.context.object
temporalScale=bpy.context.scene.render.fps
for line in file:
# Split line at ";"
print("line = %s" % line)
line = line.replace("\n","")
locRotArray = line.split(" ")
print("locRotArray = %s" % locRotArray )
#for lrt in locRotArray:
print(locRotArray[1])
obj.location = (float(locRotArray[1]), float(locRotArray[2]), float(locRotArray[3]))
# radians, and do you want XYZ, or ZYX?
obj.rotation_euler = (float(locRotArray[4]), float(locRotArray[5]), float(locRotArray[5]))
time = float(locRotArray[0])*temporalScale
print("time = %s" % time)
obj.keyframe_insert(data_path="location", frame=time)
obj.keyframe_insert(data_path="rotation_euler", frame=time)
Related
I have 1000 .txt files and planned searching for various keywords and calculate their TF-IDF Score. But for some reason the results are > 1. I did a test with 2 .txt files then: "I am studying nfc" and "You don't need AI" . For nfc and AI the TF-IDF should be 0.25 but when I open the .csv it says 1.4054651081081644.
I must admit that I did not choose the most efficient way for the code. I think the mistake is with the folders since I originally planned to check the documents by their year (annual reports from 2000-2010). But I canceled those plans and decided to check all annual reports as a whole corpus. I think the folders workaround is the problem still. I placed the 2 txt. files into the folder "-". Is there a way to make it count right?
import numpy as np
import os
from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
from pathlib import Path
# root dir
root = '/Users/Tom/PycharmProjects/TextMining/'
#
words_to_find = ['AI', 'nfc']
# tf_idf file writing
wrote_tf_idf_header = False
tf_idf_file_idx = 0
#
vectorizer_tf_idf = TfidfVectorizer(max_df=.80, min_df=1, stop_words='english', use_idf=True, norm=None, vocabulary=words_to_find, ngram_range=(1, 3))
vectorizer_cnt = CountVectorizer(stop_words='english', vocabulary=words_to_find, ngram_range=(1, 3))
#
years = ['-']
year_folders = [root + folder for folder in years]
# remove previous results file
if os.path.isfile('summary.csv'):
os.remove('summary.csv')
if os.path.isfile('tf_idf.csv'):
os.remove('tf_idf.csv')
#process every folder (for every year)
for year_idx, year_folder in enumerate(year_folders):
# get file paths in folder
file_paths = []
for file in Path(year_folder).rglob("*.txt"):
file_paths.append(file)
# count of files for each year
file_cnt = len(file_paths)
# read every file's text as string
docs_per_year = []
words_in_folder = 0
for txt_file in file_paths:
with open(txt_file, encoding='utf-8', errors="replace") as f:
txt_file_as_string = f.read()
words_in_folder += len(txt_file_as_string.split())
docs_per_year.append(txt_file_as_string)
#
tf_idf_documents_as_array = vectorizer_tf_idf.fit_transform(docs_per_year).toarray()
# tf_idf_documents_as_array = vectorizer_tf_idf.fit_transform([' '.join(docs_per_year)]).toarray()
#
cnt_documents_as_array = vectorizer_cnt.fit_transform(docs_per_year).toarray()
#
with open('summary.csv', 'a') as f:
f.write('Index;Term;Count;Df;Idf;Rel. Frequency\n')
for idx, word in enumerate(words_to_find):
abs_freq = cnt_documents_as_array[:, idx].sum()
f.write('{};{};{};{};{};{}\n'.format(idx + 1,
word,
np.count_nonzero(cnt_documents_as_array[:, idx]),
abs_freq,
vectorizer_tf_idf.idf_[idx],
abs_freq / words_in_folder))
f.write('\n')
with open('tf_idf.csv', 'a') as f:
if not wrote_tf_idf_header:
f.write('{}\n'.format(years[year_idx]))
f.write('Index;Year;File;')
for word in words_to_find:
f.write('{};'.format(word))
f.write('Sum\n')
wrote_tf_idf_header = True
for idx, tf_idfs in enumerate(tf_idf_documents_as_array):
f.write('{};{};{};'.format(tf_idf_file_idx, years[year_idx], file_paths[idx].name))
for word_idx, _ in enumerate(words_to_find):
f.write('{};'.format(tf_idf_documents_as_array[idx][word_idx]))
f.write('{}\n'.format(sum(tf_idf_documents_as_array[idx])))
tf_idf_file_idx += 1
print()
I think the mistake is, that you are defining the norm as norm=None, but the norm should be l1 or l2 as specified in the documentation.
I have books in pdf and I want to do NLP tasks such as preprocessing, tf-idf calculation, word2vec, etc on those books. So I converted them into .txt files and was trying to get tf-idf scores. Previously I performed tf-idf on a CSV file, so I made some changes in that code and tried to use it for .txt file. But I am unsuccessful in my attempt.
Below is my code:
import pandas as pd
import numpy as np
from itertools import islice
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
data = open('jungle book.txt', 'r+')
# print(data.read())
cvec = CountVectorizer(stop_words='english', min_df=1, max_df=.5, ngram_range=(1,2))
cvec.fit(data)
list(islice(cvec.vocabulary_.items(), 20))
len(cvec.vocabulary_)
cvec_count = cvec.transform(data)
print('Sparse Matrix Shape : ', cvec_count.shape)
print('Non Zero Count : ', cvec_count.nnz)
print('sparsity: %.2f%%' % (100 * cvec_count.nnz / (cvec_count.shape[0] * cvec_count.shape[1])))
occ = np.asarray(cvec_count.sum(axis=0)).ravel().tolist()
count_df = pd.DataFrame({'term': cvec.get_feature_names(), 'occurrences' : occ})
term_freq = count_df.sort_values(by='occurrences', ascending=False).head(20)
print(term_freq)
transformer = TfidfTransformer()
transformed_weights = transformer.fit_transform(cvec_count)
weights = np.asarray(transformed_weights.mean(axis=0)).ravel().tolist()
weight_df = pd.DataFrame({'term' : cvec.get_feature_names(), 'weight' : weights})
tf_idf = weight_df.sort_values(by='weight', ascending=False).head(20)
print(tf_idf)
This code is working until print ('Non Zero Count :', cvec_count.shape) and printing:
Sparse Matrix Shape : (0, 7132)
Non Zero Count : 0
Then it is giving error:
ZeroDivisionError: division by zero
Even if I run this code with ignoring ZeroDivisionError, still it is wrong as it is not counting any frequencies.
I have no idea how to work around .txt file. What is the proper way to work on .txt file for NLP tasks?
Thanks in advance!
You are getting the error because data variable is empty or wrong type. Just opening the text file is not enough. You have to read the contents into a string variable and then do the preprocessing on that variable. Try replacing
data = open('jungle book.txt', 'r+')
# print(data.read())
with
with open('jungle book.txt', 'r') as file:
data = file.read()
I'm trying to convert all type of images in a folder to text using python tesseract. Below is the that I'm using, with this only .png files are being converted to .txt, and other types are not being converted to text.
import os
import pytesseract
import cv2
import re
import glob
import concurrent.futures
import time
def ocr(img_path):
out_dir = "Output//"
img = cv2.imread(img_path)
text = pytesseract.image_to_string(img,lang='eng',config='--psm 6')
out_file = re.sub(".png",".txt",img_path.split("\\")[-1])
out_path = out_dir + out_file
fd = open(out_path,"w")
fd.write("%s" %text)
return out_file
os.environ['OMP_THREAD_LIMIT'] = '1'
def main():
path = input("Enter the path : ")
if os.path.isdir(path) == 1:
out_dir = "ocr_results//"
if not os.path.exists(out_dir):
os.makedirs(out_dir)
with concurrent.futures.ProcessPoolExecutor(max_workers=4) as executor:
image_list = glob.glob(path+"\\*.*")
for img_path,out_file in zip(image_list,executor.map(ocr,image_list)):
print(img_path.split("\\")[-1],',',out_file,', processed')
if __name__ == '__main__':
start = time.time()
main()
end = time.time()
print(end-start)
How to convert all type of image files to text. Please help me with the above code.
There is a bug in the ocr function.
First of all, the following does convert all type of image files to text.
text = pytesseract.image_to_string(img,lang='eng',config='--psm 6'))
However, what the next chunk of code does are
Select those file with .png extension using a regex
Create a new path with the same filename and a a .txt extension
Write the OCR output to the newly create text file.
out_file = re.sub(".png",".txt",img_path.split("\\")[-1])
out_path = out_dir + out_file
fd = open(out_path,"w")
fd.write("%s" %text)
In other words, all types of images files are converted but not all are written back correctly. The regex matching logic only replace .png with .txt and assign to out_path. When there is no .png (other image types), the variable gets the same value as the original filename (e.g. sampe.jpg). The next lines of code open the original image and overwrite with the OCR result.
One way to fix is by adding all the image formats you want to cover into the regex.
For example,
out_file = re.sub(".png|.jpg|.bmp|.tiff",".txt",img_path.split("\\")[-1])
I learn how to convert DCM file to Raw file .Got the code from Git Hub:
https://github.com/xiasun/dicom2raw/blob/master/dicom2raw.py
And it got a error"Can't convert 'bytes' object to str implicitly" on the line
"allInOne += dataset.PixelData"
I try to use "encode("utf-8")",but it make allInOne to be empty.
By the way ,Is there any code to generate the .mhd file corresponding to the .raw file?
import dicom
import os
import numpy
import sys
dicomPath = "C:/DataLuna16pen/dcmdata/"
lstFilesDCM = [] # create an empty list
for dirName, subdirList, fileList in os.walk(dicomPath):
allInOne = ""
print(subdirList)
i=0
for filename in fileList:
i+=1
if "".join(filename).endswith((".dcm", ".DCM")):
path = dicomPath + "".join(filename)
dataset = dicom.read_file(path)
for n,val in enumerate(dataset.pixel_array.flat):
dataset.pixel_array.flat[n] = val / 60
if val < 0:
dataset.pixel_array.flat[n] = 0
dataset.PixelData = numpy.uint8(dataset.pixel_array).tostring()
allInOne += dataset.PixelData
print ("slice " + "".join(filename) + " done ",end=" ")
print (i)
newFile = open("./all_in_one.raw", "wb")
newFile.write(allInOne)
newFile.close()
print ("RAW file generated")
There are several things:
PyDicom still doesn't read compressed DICOMs properly (loseless jpeg). You should check Transfer Syntax of the files to check if this is the case. As a workaround you can use GDCM tool dcmdjpeg
you should not convert byte array into string (np.array.tostring returns in fact the array of bytes)
for writing mha files, take a look at MedPy. You can also use ITK directly. There is python wrapper and SimpleITK - some kind lightweight modification of ITK
For those that want to export a simple 3D numpy array (along with axes) to a .vtk (or .vtr) file for post-processing and display in Paraview or Mayavi there's a little module called PyEVTK that does exactly that. The module supports structured and unstructured data etc..
Unfortunately, even though the code works fine in unix-based systems I couldn't make it work (keeps crashing) on any windows installation which simply makes things complicated. Ive contacted the developer but his suggestions did not work
Therefore my question is:
How can one use the from vtk.util import numpy_support function to export a 3D array (the function itself doesn't support 3D arrays) to a .vtk file? Is there a simple way to do it without creating vtkDatasets etc etc?
Thanks a lot!
It's been forever and I had entirely forgotten asking this question but I ended up figuring it out. I've written a post about it in my blog (PyScience) providing a tutorial on how to convert between NumPy and VTK. Do take a look if interested:
pyscience.wordpress.com/2014/09/06/numpy-to-vtk-converting-your-numpy-arrays-to-vtk-arrays-and-files/
It's not a direct answer to your question, but if you have tvtk (if you have mayavi, you should have it), you can use it to write your data to vtk format. (See: http://code.enthought.com/projects/files/ETS3_API/enthought.tvtk.misc.html )
It doesn't use PyEVTK, and it supports a broad range of data sources (more than just structured and unstructured grids), so it will probably work where other things aren't.
As a quick example (Mayavi's mlab interface can make this much less verbose, especially if you're already using it.):
import numpy as np
from enthought.tvtk.api import tvtk, write_data
data = np.random.random((10,10,10))
grid = tvtk.ImageData(spacing=(10, 5, -10), origin=(100, 350, 200),
dimensions=data.shape)
grid.point_data.scalars = np.ravel(order='F')
grid.point_data.scalars.name = 'Test Data'
# Writes legacy ".vtk" format if filename ends with "vtk", otherwise
# this will write data using the newer xml-based format.
write_data(grid, 'test.vtk')
And a portion of the output file:
# vtk DataFile Version 3.0
vtk output
ASCII
DATASET STRUCTURED_POINTS
DIMENSIONS 10 10 10
SPACING 10 5 -10
ORIGIN 100 350 200
POINT_DATA 1000
SCALARS Test%20Data double
LOOKUP_TABLE default
0.598189 0.228948 0.346975 0.948916 0.0109774 0.30281 0.643976 0.17398 0.374673
0.295613 0.664072 0.307974 0.802966 0.836823 0.827732 0.895217 0.104437 0.292796
0.604939 0.96141 0.0837524 0.498616 0.608173 0.446545 0.364019 0.222914 0.514992
...
...
TVTK of Mayavi has a beautiful way of writing vtk files. Here is a test example I have written for myself following #Joe and tvtk documentation. The advantage it has over evtk, is the support for both ascii and html.Hope it will help other people.
from tvtk.api import tvtk, write_data
import numpy as np
#data = np.random.random((3, 3, 3))
#
#i = tvtk.ImageData(spacing=(1, 1, 1), origin=(0, 0, 0))
#i.point_data.scalars = data.ravel()
#i.point_data.scalars.name = 'scalars'
#i.dimensions = data.shape
#
#w = tvtk.XMLImageDataWriter(input=i, file_name='spoints3d.vti')
#w.write()
points = np.array([[0,0,0], [1,0,0], [1,1,0], [0,1,0]], 'f')
(n1, n2) = points.shape
poly_edge = np.array([[0,1,2,3]])
print n1, n2
## Scalar Data
#temperature = np.array([10., 20., 30., 40.])
#pressure = np.random.rand(n1)
#
## Vector Data
#velocity = np.random.rand(n1,n2)
#force = np.random.rand(n1,n2)
#
##Tensor Data with
comp = 5
stress = np.random.rand(n1,comp)
#
#print stress.shape
## The TVTK dataset.
mesh = tvtk.PolyData(points=points, polys=poly_edge)
#
## Data 0 # scalar data
#mesh.point_data.scalars = temperature
#mesh.point_data.scalars.name = 'Temperature'
#
## Data 1 # additional scalar data
#mesh.point_data.add_array(pressure)
#mesh.point_data.get_array(1).name = 'Pressure'
#mesh.update()
#
## Data 2 # Vector data
#mesh.point_data.vectors = velocity
#mesh.point_data.vectors.name = 'Velocity'
#mesh.update()
#
## Data 3 additional vector data
#mesh.point_data.add_array( force)
#mesh.point_data.get_array(3).name = 'Force'
#mesh.update()
mesh.point_data.tensors = stress
mesh.point_data.tensors.name = 'Stress'
# Data 4 additional tensor Data
#mesh.point_data.add_array(stress)
#mesh.point_data.get_array(4).name = 'Stress'
#mesh.update()
write_data(mesh, 'polydata.vtk')
# XML format
# Method 1
#write_data(mesh, 'polydata')
# Method 2
#w = tvtk.XMLPolyDataWriter(input=mesh, file_name='polydata.vtk')
#w.write()
I know it is a bit late and I do love your tutorials #somada141. This should work too.
def numpy2VTK(img, spacing=[1.0, 1.0, 1.0]):
# evolved from code from Stou S.,
# on http://www.siafoo.net/snippet/314
# This function, as the name suggests, converts numpy array to VTK
importer = vtk.vtkImageImport()
img_data = img.astype('uint8')
img_string = img_data.tostring() # type short
dim = img.shape
importer.CopyImportVoidPointer(img_string, len(img_string))
importer.SetDataScalarType(VTK_UNSIGNED_CHAR)
importer.SetNumberOfScalarComponents(1)
extent = importer.GetDataExtent()
importer.SetDataExtent(extent[0], extent[0] + dim[2] - 1,
extent[2], extent[2] + dim[1] - 1,
extent[4], extent[4] + dim[0] - 1)
importer.SetWholeExtent(extent[0], extent[0] + dim[2] - 1,
extent[2], extent[2] + dim[1] - 1,
extent[4], extent[4] + dim[0] - 1)
importer.SetDataSpacing(spacing[0], spacing[1], spacing[2])
importer.SetDataOrigin(0, 0, 0)
return importer
Hope it helps!
Here's a SimpleITK version with the function load_itk taken from here:
import SimpleITK as sitk
import numpy as np
if len(sys.argv)<3:
print('Wrong number of arguments.', file=sys.stderr)
print('Usage: ' + __file__ + ' input_sitk_file' + ' output_sitk_file', file=sys.stderr)
sys.exit(1)
def quick_read(filename):
# Read image information without reading the bulk data.
file_reader = sitk.ImageFileReader()
file_reader.SetFileName(filename)
file_reader.ReadImageInformation()
print('image size: {0}\nimage spacing: {1}'.format(file_reader.GetSize(), file_reader.GetSpacing()))
# Some files have a rich meta-data dictionary (e.g. DICOM)
for key in file_reader.GetMetaDataKeys():
print(key + ': ' + file_reader.GetMetaData(key))
def load_itk(filename):
# Reads the image using SimpleITK
itkimage = sitk.ReadImage(filename)
# Convert the image to a numpy array first and then shuffle the dimensions to get axis in the order z,y,x
data = sitk.GetArrayFromImage(itkimage)
# Read the origin of the ct_scan, will be used to convert the coordinates from world to voxel and vice versa.
origin = np.array(list(reversed(itkimage.GetOrigin())))
# Read the spacing along each dimension
spacing = np.array(list(reversed(itkimage.GetSpacing())))
return data, origin, spacing
def convert(data, output_filename):
image = sitk.GetImageFromArray(data)
writer = sitk.ImageFileWriter()
writer.SetFileName(output_filename)
writer.Execute(image)
def wait():
print('Press Enter to load & convert or exit using Ctrl+C')
input()
quick_read(sys.argv[1])
print('-'*20)
wait()
data, origin, spacing = load_itk(sys.argv[1])
convert(sys.argv[2])