It's a two part question,
import face_recognition
import os
import json
loadarr=[]
encodearr=[]
for i in range(0, 4):
loadarr.append(face_recognition.load_image_file( "brad"+str(i+1)+".jpg"))
encodearr.append(face_recognition.face_encodings(loadarr[i])[0])
encodearr = encodearr.tolist()
# print(encodearr)
encodedDic = {"des": encodearr}
with open("sample.json", "w") as outfile:
json.dump(encodedDic,outfile)
When I tried to convert the list encodearr as value of the key "des" (without .tolist()) it shows
TypeError: Object of type ndarray is not JSON serializable .Then I added .tolist() to encode arr as show. it shows AttributeError: 'list' object has no attribute 'tolist', brad1 to brad5 are the jpg files in the directory.
I did a workaround using numpy.
import face_recognition
import os
import json
import numpy as np
encodearr=[]
for i in range(0, 4):
load=face_recognition.load_image_file( "brad"+str(i+1)+".jpg")
encodearr.append(face_recognition.face_encodings(loadarr)[0])
reshapped_array = np.reshape(encodearr,(total_images,128) //each image is an array consisting 128 images
encodedDic = {"des": reshapped_array }
with open("sample.json", "w") as outfile:
json.dump(encodedDic,outfile)
Related
I have a .csv file which has /raw_points rostopic, and i'm trying to convert that file into PointCloud2 data(http://docs.ros.org/en/api/sensor_msgs/html/msg/PointCloud2.html).
import csv
import sys
csv.field_size_limit(sys.maxsize)
file = open("points_raw.csv")
csvreader = csv.reader(file)
header = next(csvreader)
print(header)
This is my header:
['Time', 'header.seq', 'header.stamp.secs', 'header.stamp.nsecs', 'header.frame_id', 'height', 'width', 'fields', 'is_bigendian', 'point_step', 'row_step', 'data', 'is_dense']
These information match the CloudPoint2, but I'm not sure how to convert it to this type.
You need to simply iterate over each row and for every row store the relative fields in a PointCloud2 message and publish it out. For example:
import rospy
import csv
from sensor_msgs.msg import PointCloud2
def main():
#Setup ros param/init here
some_pub = rospy.Publisher('output_topic', PointCloud2, queue_size=10)
with open('some_file.csv', 'r') as f:
reader = csv.reader(f)
for line in reader:
split_line = line.split(',')
new_msg = PointCloud2()
new_msg.header.seq = split_line[1]
new_msg.header.stamp.secs = split_line[2]
#Iterate over the rest
new_msg.data = split_line[11]
new_msg.is_dense = split_line[12]
some_pub.publish(new_msg)
rospy.Rate(10).sleep() #Sleep at 10Hz
I would like to compare log and pct change f the two symbols, but the following error appears:
KeyError: 'Adj Close'
import datetime
import pandas as pd
import numpy as np
import yfinance as yf
start = datetime.datetime(2017, 10, 1)
end = datetime.datetime.now()
symbols = ['BTC-USD', 'ETH-USD']
df = pd.DataFrame()
for i in symbols:
data = yf.download(i, start=None, end=None,show_errors=("True"),
period="4y", interval="1mo")
df[i] = data['Adj Close'].pct_change().dropna()
df['log_stuff'] = \
np.log(df['Adj Close'].astype('float64')/df['Adj Close'].astype('float64').shift(1))
df[['pct_change', 'log_stuff','df']].plot();
You could try the following. Please note, that you can also pass a list to download(), so no loops are required.
import numpy as np
import pandas as pd
import yfinance as yf
symbols = ['BTC-USD', 'ETH-USD']
data = yf.download(symbols, period="4y", interval="1mo")
# calculate pct return
pct_data = data['Adj Close'].pct_change()
pct_data = pct_data.add_suffix('_pct')
# calculate log returns
log_data = np.log(data['Adj Close']) - np.log(data['Adj Close'].shift(1))
log_data = log_data.add_suffix('_log')
# combine returns and drop na values
combined_data = pd.concat([pct_data,log_data], axis=1).dropna()
print(combined_data)
This will yield the following output:
BTC-USD_pct ETH-USD_pct BTC-USD_log ETH-USD_log
Date
2017-12-01 0.383326 0.692483 0.324490 0.526197
2018-01-01 -0.277987 0.477813 -0.325713 0.390564
2018-02-01 0.017298 -0.235276 0.017150 -0.268240
...
So I am trying to read a txt file, process it by taking out the stop words, and then output that result into a new file. However, I keep getting the following error:
TypeError: expected a string or other character buffer object
This is my code:
import nltk
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
f=open('tess1.txt','rU')
stop_words = set(stopwords.words('english'))
raw=f.read()
word_tokens = word_tokenize(raw)
text = nltk.Text(word_tokens)
filtered_sentence = [w for w in word_tokens if not w in stop_words]
if w not in stop_words:
filtered_sentence.append(w)
K = open("tess12.txt", "w")
K.write(filtered_sentence)
K.close()
print(filtered_sentence)
The solution's to write a string inside the buffer:
K.write(str(filtered_sentence))
I am beginner of python language,natural language processing,deep learning,neural networks.I want to execute a program which convert text file into vector by using word2vec in python..someone please help me
import math
import nltk file = "/home/stephy/Demo/textfile.txt"
import numpy as np
def loadGloveModel(gloveFile):
with open(gloveFile, encoding="utf8" ) as f:
content = f.readlines()
model = {} for line in content:
splitLine = line.split()
word = splitLine[0]
embedding = np.array([float(val) for val in splitLine[1:]])
model[word] = embedding
print ("Done.",len(model)," words loaded!")
return model
model= loadGloveModel(file)
print (model['file'])
I have a dask data frame where the index is a string which looks like this:
12/09/2016 00:00;32.0046;-106.259
12/09/2016 00:00;32.0201;-108.838
12/09/2016 00:00;32.0224;-106.004
(its basically a string encoding the datetime;latitude;longitude of the row)
I'd like to split that while still in the dask context to individual columns representing each of the fields.
I can do that with a pandas dataframe as:
df['date'], df['Lat'], df['Lon'] = df.index.str.split(';', 2).str
But that doesn't work in dask for several of the attempts I've tried. If I directly substitute the df for a dask df I get the error:
'Index' object has no attribute 'str'
If I use the column name instead of index as:
forecastDf['date'], forecastDf['Lat'], forecastDf['Lon'] = forecastDf['dateLocation'].str.split(';', 2).str
I get the error:
TypeError: 'StringAccessor' object is not iterable
Here is an runnable example of this working in Pandas
import pandas as pd
df = pd.DataFrame()
df['dateLocation'] = ['12/09/2016 00:00;32.0046;-106.259','12/09/2016 00:00;32.0201;-108.838','12/09/2016 00:00;32.0224;-106.004']
df = df.set_index('dateLocation')
df['date'], df['Lat'], df['Lon'] = df.index.str.split(';', 2).str
df.head()
Here is the error I get if I directly convert that to dask
import dask.dataframe as dd
dd = dd.from_pandas(df, npartitions=1)
dd['date'], dd['Lat'], dd['Lon'] = dd.index.str.split(';', 2).str
>>TypeError: 'StringAccessor' object is not iterable
forecastDf['date'] = forecastDf['dateLocation'].str.partition(';')[0]
forecastDf['Lat'] = forecastDf['dateLocation'].str.partition(';')[2]
forecastDf['Lon'] = forecastDf['dateLocation'].str.partition(';')[4]
Let me know if this works for you!
First make sure the column is string dtype
forecastDD['dateLocation'] = forecastDD['dateLocation'].astype('str')
Then you can use this to split in dask
splitColumns = client.persist(forecastDD['dateLocation'].str.split(';',2))
You can then index the columns in the new dataframe splitColumns and add them back to the original data frame.
forecastDD = forecastDD.assign(Lat=splitColumns.apply(lambda x: x[0], meta=('Lat', 'f8')), Lon=splitColumns.apply(lambda x: x[1], meta=('Lat', 'f8')), date=splitColumns.apply(lambda x: x[2], meta=('Lat', np.dtype(str))))
Unfortunately I couldn't figure out how to do it without calling compute and creating the temp dataframe.