I have a date string in microsecond resolution. I need it as an integer.
import pandas as pd
data = ["20181231235959383171", "20181231235959383172"]
df = pd.DataFrame(data=data, columns=["A"])
df["A"].astype(np.int)
Error:
File "pandas\_libs\lib.pyx", line 545, in pandas._libs.lib.astype_intsafe
OverflowError: Python int too large to convert to C long
Same problem if I try to cast it to standard Python int
Per my answer in your previous question:
import pandas as pd
data = ["20181231235959383171", "20181231235959383172"]
df = pd.DataFrame(data=data, columns=["A"])
# slow but big enough
df["A_as_python_int"] = df["A"].apply(int)
# fast but has to be split to two integers
df["A_seconds"] = (df["A_as_python_int"] // 1000000).astype(np.int)
df["A_fractions"] = (df["A_as_python_int"] % 1000000).astype(np.int)
You could do this:
import pandas as pd
data = ["20181231235959383171", "20181231235959383172"]
df = pd.DataFrame(data=data, columns=["A"])
before = df.A[0]
df.A = [int(x) for x in df.A.tolist()]
after = df.A[0]
before, after
Output:
The data has been cast into an integer. Showing: (before, after)
('20181231235959383171', 20181231235959383171)
Related
My dtype is changing after i unhash the foo and groupby i get # we require a list, but not a 'str'.
I wanted if the value (in my case Date) in the 1 column is the same then the text from the 3 column goes there after a ',' sign, in my final project
import os
import pandas as pd
import dateutil
from pandas import DataFrame
from datetime import datetime, timedelta
data_file_folder = '.\Data'
df = []
for file in os.listdir(data_file_folder):
if file.endswith('.xlsx'):
print('Loading File {0}...'.format(file))
df.append(pd.read_excel(os.path.join(data_file_folder,file),sheet_name='Sheet1'))
df_master = pd.concat(df,axis=0)
df_master['Date'] = df_master['Date'].dt.date
#foo = lambda a: ", ".join(a)
#df_master = df_master.groupby(by='Date').agg({'Tweet': foo}).reset_index()
#df_master.to_excel('.\NewFolder\example.xlsx',index=False)
#df_master
import pandas as pd
import numpy as np
from sklearn.preprocessing import Imputer
data = pd.read_csv("austin_weather.csv")
data = data.drop(['Events', 'Date'], axis = 1)
X = data.iloc[:, :-1].values
Y = data.iloc[:, 18].values
data = data.replace('T', 0.0)
imputer = Imputer(missing_values="-", strategy="mean", axis = 0)
imputer.fit(X[:])
the imputer function is not able to convert the "-" blank value to the mean of the respective column
For the depreciated class sklearn.preprocessing.Imputer parameter missing_values is either string NaN or a number.
So you can first replace all - values with np.nan: X.replace('-', np.nan) and then call imputer.
Iam using rpy2 to get comorbidity Index of patients , i got the results but iam not able to convert those output to pandas Dataframe
below is the code
#creating Datframe
data = {"person_id":[1,1,1,2,2,3],
"dx_1":["F11","E40","","F32","C77","G10"],
"dx_2":["F1P","E400","","F322","C737",""]}
#converting Pandas Dataframe to R Datframe using rpy2
import rpy2
from rpy2.robjects import pandas2ri
import rpy2.robjects.numpy2ri
from rpy2.robjects.packages import importr
r_dataframe = pandas2ri.py2ri(df1)
print(r_dataframe)
#installing 'comorbidity ' package using rpy2
R = rpy2.robjects.r
DTW = importr('comorbidity')
#executing comorbidity function by using one column icd_1
output = DTW.comorbidity(x = r_dataframe, id = "person_id", code = "icd_1",
score = "charlson", assign0 = False,
icd = "icd10")
print(output)
but not able to convert output to pandas dataframe
import rpy2, rpy2.robjects as robjects, rpy2.robjects.packages as rpackages
from rpy2.robjects.vectors import StrVector
#Converting data frames back and forth between rpy2 and pandas
from rpy2.robjects import r, pandas2ri
#convert output to pandas dataframe
pandas2ri.ri2py_dataframe(output)
getting below error
TypeError: Parameter 'categories' must be list-like, was
please help
Thanks in advance
I'm trying to find inter-purchase times (i.e., days between orders) for customers. Although my code is working correctly without defining meta, I would like to get it working properly and no longer see the warning asking me to provide meta.
Also, I would appreciate any suggestions on how to use map or map_partitions instead of apply.
So far I've tried:
meta={'days_since_last_order': 'datetime64[ns]'}
meta={'days_since_last_order': 'f8'}
meta={'ORDER_DATE_DT':'datetime64[ns]','days_since_last_order': 'datetime64[ns]'}
meta={'ORDER_DATE_DT':'f8','days_since_last_order': 'f8'}
meta=('days_since_last_order', 'f8')
meta=('days_since_last_order', 'datetime64[ns]')
Here is my code:
import numpy as np
import pandas as pd
import datetime as dt
import dask.dataframe as dd
from dask.distributed import wait, Client
client = Client(processes=True)
start = pd.to_datetime('2015-01-01')
end = pd.to_datetime('2018-01-01')
d = (end - start).days + 1
np.random.seed(0)
df = pd.DataFrame()
df['CUSTOMER_ID'] = np.random.randint(1, 4, 10)
df['ORDER_DATE_DT'] = start + pd.to_timedelta(np.random.randint(1, d, 10), unit='d')
print(df.sort_values(['CUSTOMER_ID','ORDER_DATE_DT']))
print(df)
ddf = dd.from_pandas(df, npartitions=2)
# setting ORDER_DATE_DT as index to sort by date
ddf = ddf.set_index('ORDER_DATE_DT')
ddf = client.persist(ddf)
wait(ddf)
ddf = ddf.reset_index()
grp = ddf.groupby('CUSTOMER_ID')[['ORDER_DATE_DT']].apply(
lambda df: df.assign(days_since_last_order=df.ORDER_DATE_DT.diff(1))
# meta=????
)
# for some reason, I'm unable to print grp unless I reset_index()
grp = grp.reset_index()
print(grp.compute())
Here is the printout of df.sort_values(['CUSTOMER_ID','ORDER_DATE_DT'])
Here is the printout of grp.compute()
import pandas as pd
data = {'x':['011','012','013'],'y':['022','033','041']}
Df = pd.DataFrame(data = data,type = str)
Df.to_csv("path/to/save.csv")
There result I've obtained seems as this
To achieve such result it will be easier to export directly to xlsx file, even without setting dtype of DataFrame.
import pandas as pd
writer = pd.ExcelWriter('path/to/save.xlsx')
data = {'x':['011','012','013'],'y':['022','033','041']}
Df = pd.DataFrame(data = data)
Df.to_excel(writer,"Sheet1")
writer.save()
I've tried also some other methods like prepending apostrophe or quoting all fields with ", but it gave no effect.