I have to import a processed h5ad file, but it seems that X has been passed as a numpy array instead of a numpy matrix. See below:
# Read the data
data_path = "/home/bbb5130/snOMICS/maria/msrna.h5ad"
adata = sn.pp.read_h5ad(data_path, pr_process="Yes")
adata
But the output was:
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
Cell In [15], line 3
1 # Read the data
2 data_path = "/home/bbb5130/snOMICS/maria/msrna.h5ad"
----> 3 adata = sn.pp.read_h5ad(data_path, pr_process="Yes")
4 adata
File ~/miniconda3/envs/snOMICS/lib/python3.9/site-packages/scanet/preprocessing.py:54, in Preprocessing.read_h5ad(cls, filename, pr_process)
51 return sc.read_h5ad(filename)
52 else:
53 # initial preprocessing as it is required later
---> 54 return cls._intial(adata)
File ~/miniconda3/envs/snOMICS/lib/python3.9/site-packages/scanet/preprocessing.py:35, in Preprocessing._intial(adata)
33 adata.var['mt'] = adata.var_names.str.startswith('MT-')
34 mito_genes = adata.var_names.str.startswith('MT-')
---> 35 adata.obs['percent_mito'] = np.sum(adata[:, mito_genes].X, axis=1).A1 / np.sum(adata.X, axis=1).A1
36 sc.pp.calculate_qc_metrics(adata, qc_vars=['mt'], percent_top=None, inplace=True)
37 sc.pp.filter_cells(adata, min_genes=0)
AttributeError: 'ArrayView' object has no attribute 'A1'
Is there anyway I can change the format, so the file can be read?
Thanks in advance.
I wanna stemming my dataset. Before stemming, I did tokenize use nltk tokenize
You can see the output on the pic
Dataset
Col Values
But when i do stemming, it return error :
[Error][3]
TypeError Traceback (most recent call
last)
<ipython-input-102-7700a8e3235b> in <module>()
----> 1 df['Message'] = df['Message'].apply(stemmer.stem)
2 df = df[['Message', 'Category']]
3 df.head()
5 frames
/usr/local/lib/python3.7/dist-
packages/Sastrawi/Stemmer/Filter/TextNormalizer.py in
normalize_text(text)
2
3 def normalize_text(text):
----> 4 result = str.lower(text)
5 result = re.sub(r'[^a-z0-9 -]', ' ', result, flags =
re.IGNORECASE|re.MULTILINE)
6 result = re.sub(r'( +)', ' ', result, flags =
re.IGNORECASE|re.MULTILINE)
TypeError: descriptor 'lower' requires a 'str' object but received a
'list'
Hope all you guys can help me
Ive'been trying to transform all my logs in a dict through xmltodict.parse function
The thing is, when I try to convert a single row to a variable it works fine
a = xmltodict.parse(df['CONFIG'][0])
Same to
parsed[1] = xmltodict.parse(df['CONFIG'][1])
But when I try to iterate the entire dataframe and store it on a dictionaire I get the following
for ind in df['CONFIG'].index:
parsed[ind] = xmltodict.parse(df['CONFIG'][ind])
---------------------------------------------------------------------------
ExpatError Traceback (most recent call last)
/tmp/ipykernel_31/1871123186.py in <module>
1 for ind in df['CONFIG'].index:
----> 2 parsed[ind] = xmltodict.parse(df['CONFIG'][ind])
/opt/conda/lib/python3.9/site-packages/xmltodict.py in parse(xml_input, encoding, expat, process_namespaces, namespace_separator, disable_entities, **kwargs)
325 parser.ParseFile(xml_input)
326 else:
--> 327 parser.Parse(xml_input, True)
328 return handler.item
329
ExpatError: syntax error: line 1, column 0
Can you try this?
for ind in range(len(df['CONFIG'])):
parsed[ind] = xmltodict.parse(df['CONFIG'][ind])
I am new to python. I am getting an error when running below code. The issue seems to be with date. can someone help me to correct i please. I have tried changing the date format in the excel but it does not solve the issue. The excel have a list of several bonds. I want to generate the coupon dates of the different bonds
BondData = pd.read_excel (r'C:\Users\Avishen\Desktop\Python\BONDDATA.xlsx')
Data = pd.DataFrame(BondData)
def scheduledates():
tenor = ql.Period(ql.Semiannual)
day_count = ql.Thirty360
calendar = ql.UnitedStates()
businessConvention = ql.Unadjusted
dateGeneration = ql.DateGeneration.Backward
monthEnd = False
# Dates in Bond Period
return ql.Schedule (issueDate, maturityDate, tenor, calendar, businessConvention,
businessConvention , dateGeneration, monthEnd)
new_df["Dates"]= Data.apply(lambda x: scheduledates(),axis = 1)
new_df["ISIN"] = Data.ISIN
new_df
Error:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-4-877415e9cf83> in <module>
21 businessConvention , dateGeneration, monthEnd)
22
---> 23 new_df["Dates"]= Data.apply(lambda x: scheduledates(),axis = 1)
24 new_df["ISIN"] = Data.ISIN
25 new_df
~\anaconda3\lib\site-packages\pandas\core\frame.py in apply(self, func, axis, raw, result_type, args, **kwds)
7546 kwds=kwds,
7547 )
-> 7548 return op.get_result()
7549
7550 def applymap(self, func) -> "DataFrame":
~\anaconda3\lib\site-packages\pandas\core\apply.py in get_result(self)
178 return self.apply_raw()
179
--> 180 return self.apply_standard()
181
182 def apply_empty_result(self):
~\anaconda3\lib\site-packages\pandas\core\apply.py in apply_standard(self)
269
270 def apply_standard(self):
--> 271 results, res_index = self.apply_series_generator()
272
273 # wrap results
~\anaconda3\lib\site-packages\pandas\core\apply.py in apply_series_generator(self)
298 for i, v in enumerate(series_gen):
299 # ignore SettingWithCopy here in case the user mutates
--> 300 results[i] = self.f(v)
301 if isinstance(results[i], ABCSeries):
302 # If we have a view on v, we need to make a copy because
<ipython-input-4-877415e9cf83> in <lambda>(x)
21 businessConvention , dateGeneration, monthEnd)
22
---> 23 new_df["Dates"]= Data.apply(lambda x: scheduledates(),axis = 1)
24 new_df["ISIN"] = Data.ISIN
25 new_df
<ipython-input-4-877415e9cf83> in scheduledates()
8
9 def scheduledates():
---> 10 issueDate = ql.Date(Data.issuedate)
11 maturityDate = ql.Date(Data.maturitydate)
12 tenor = ql.Period(ql.Semiannual)
~\anaconda3\lib\site-packages\QuantLib\QuantLib.py in __init__(self, *args)
425
426 def __init__(self, *args):
--> 427 _QuantLib.Date_swiginit(self, _QuantLib.new_Date(*args))
428
429 def weekdayNumber(self):
TypeError: Wrong number or type of arguments for overloaded function 'new_Date'.
Possible C/C++ prototypes are:
Date::Date()
Date::Date(Day,Month,Year)
Date::Date(Day,Month,Year,Hour,Minute,Second,Millisecond,Microsecond)
Date::Date(Day,Month,Year,Hour,Minute,Second,Millisecond)
Date::Date(Day,Month,Year,Hour,Minute,Second)
Date::Date(BigInteger)
Date::Date(std::string const &,std::string)
---------------------------------------------------------------------------
Data = pd.DataFrame(BondData)
Fields from Bond Data
ISIN
issuedate
maturitydate
coupon
Tradeyield
Bond_Price
MarketPrice
Nominal_Amount
From the traceback, the problem is the line:
issueDate = ql.Date(Data.issuedate)
(which for some reason is not in the code you pasted). Coming from Excel, issuedate should be an integer and thus compatible with the ql.Date constructor, but it's possible that pandas is reading it as a string or some other type. You should examine the data frame and check the type of the column. If it's not what you expect, you'll have to figure out if there are data in that column that pandas can't interpret as integers, and either clean them up of force the conversion somehow before passing them to ql.Date.
In a machine learning project, suppose I have 3 cat images and 2 dog images. when I make a dataframe for the training data.
#pre processing train data
filenames = os.listdir('/content/train')
categories = []
for filename in os.listdir('/content/train'):
category = filename.split('.')[0]
if category == 'dog' :
categories.append(1) #1 for dog and 0 for cat
else :
categories.append(0)
#make a dictonary
df = pd.DataFrame(
{
'filename' : filenames,
'category':categories
}
)
It gives an error because I haven't the same amount of dog, cat images.
ValueError Traceback (most recent call last)
<ipython-input-28-2d4e2440ba41> in <module>()
12 {
13 'filename' : filenames,
---> 14 'category' : categories
15 }
16 )
3 frames
/usr/local/lib/python3.6/dist-packages/pandas/core/internals/construction.py in extract_index(data)
395 lengths = list(set(raw_lengths))
396 if len(lengths) > 1:
--> 397 raise ValueError("arrays must all be same length")
398
399 if have_dicts:
ValueError: arrays must all be same length
Is there any way to fix it without adding any image to the training dataset?