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
I have a plot that looks like this :
import pandas as pd
import pandas_datareader as web
import datetime as dt
from datetime import timedelta
import matplotlib.pyplot as plt
#get the data
start_date = pd.to_datetime('2019-11-1')
end_date = pd.datetime.today()
df = web.DataReader('^gspc', 'yahoo', start_date, end_date)
df = df['Adj Close']
#build the plot
fig, ax1 = plt.subplots()
ax1.plot(df)
#set the axhline
ax1.axhline(df.max(),xmin=0,xmax=1)
ax1.set_xlim(start_date,end_date + timedelta(30))
ax1.set_ylim(df.min() -200, df.max() +200)
I am trying to set the axhline so it starts on the day of the maximum value in the df. I am having issues because the index is a datetime object, and axhline needs an integer.
Here is what I've tried:
ax1.axhline(df.max(),xmin=df.idxmax(),xmax=1)
What is the most efficient way to set the xmin to the date of the max value in the df?
Thanks
axhline() uses a y position, and two x positions. Y is in data coordinates and x in axes coordinates (0 for the left margin, 1 for the right). But the desired starting position is only available in data coordinates. hlines() can work with these.
df.argmax() finds the position of the maximum. df.index[df.argmax()] or df.idxmax() gets the value of the index at that position.
import pandas as pd
import pandas_datareader as web
import datetime as dt
from datetime import timedelta
import matplotlib.pyplot as plt
start_date = pd.to_datetime('2019-11-1')
end_date = pd.datetime.today()
df = web.DataReader('^gspc', 'yahoo', start_date, end_date)
df = df['Adj Close']
fig, ax1 = plt.subplots()
ax1.plot(df)
ax1.hlines(df.max(), df.idxmax(), end_date + timedelta(30), color='crimson', ls=':')
ax1.set_xlim(start_date, end_date + timedelta(30))
ax1.set_ylim(df.min() - 200, df.max() + 200)
plt.show()
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()
So I'm currently learning how to analyse financial data in python using numpy, pandas, etc... and I'm starting off with a small script that will hopefully rank some chosen equities by the price change between 2 chosen dates.
My first script was:
import numpy as np
import pandas as pd
from pandas_datareader import data as web
from pandas import Series, DataFrame
import datetime
from operator import itemgetter
#Edit below for 2 dates you wish to calculate:
start = datetime.datetime(2014, 7, 15)
end = datetime.datetime(2017, 7, 25)
stocks = ('AAPL', 'GOOGL', 'YHOO', 'MSFT', 'AMZN', 'DAI')
#Getting the data:
AAPL = web.DataReader('AAPL', 'google', start, end)
GOOGL = web.DataReader('GOOGL', 'google', start, end)
YHOO = web.DataReader('YHOO', 'google', start, end)
MSFT = web.DataReader('MSFT', 'google', start, end)
AMZN = web.DataReader('AMZN', 'google', start, end)
DAI = web.DataReader('DAI', 'google', start, end)
#Calculating the change:
AAPLkey = (AAPL.ix[start]['Close'])/(AAPL.ix[end]['Close'])
GOOGLkey = (GOOGL.ix[start]['Close'])/(GOOGL.ix[end]['Close'])
YHOOkey = (YHOO.ix[start]['Close'])/(YHOO.ix[end]['Close'])
MSFTkey = (MSFT.ix[start]['Close'])/(MSFT.ix[end]['Close'])
AMZNkey = (AMZN.ix[start]['Close'])/(AMZN.ix[end]['Close'])
DAIkey = (DAI.ix[start]['Close'])/(DAI.ix[end]['Close'])
#Formatting the output in a sorted order:
dict1 = {"AAPL" : AAPLkey, "GOOGL" : GOOGLkey, "YHOO" : YHOOkey, "MSFT" : MSFTkey, "AMZN" : AMZNkey, "DAI" : DAIkey}
out = sorted(dict1.items(), key=itemgetter(1), reverse = True)
for tick , change in out:
print (tick,"\t", change)
I now obviously want to make this far shorter and this is what I've got so far:
import numpy as np
import pandas as pd
from pandas_datareader import data as web
from pandas import Series, DataFrame
import datetime
from operator import itemgetter
#Edit below for 2 dates you wish to calculate:
start = datetime.datetime(2014, 7, 15)
end = datetime.datetime(2017, 7, 25)
stocks = ('AAPL', 'GOOGL', 'YHOO', 'MSFT', 'AMZN', 'DAI')
for eq in stocks:
eq = web.DataReader(eq, 'google', start, end)
for legend in eq:
legend = (eq.ix[start]['Close'])/(eq.ix[end]['Close'])
print (legend)
The calculation works BUT the problem is this only outputs the last value for the item in the list (DAI).
So what's next in order to get the same result as my first code?
You can just move print statement into loop.
Like:
for legend in eq:
legend = (eq.loc[start]['Close'])/(eq.loc[end]['Close'])
print(legend)
Improved answer:
Get rid of label loop and print values from previous loop:
for eq in stocks:
df = web.DataReader(eq, 'google', start, end)
print((df.loc[start]['Close'])/(df.loc[end]['Close']))
When you loop over stocks at line for eq in stocks, you are saving results into eq. So at each iteration it gets overwritten. You should store the results in a list, like I have done using data.
Then loop over the data list which contains dataframes, and then use proper selection.
import numpy as np
import pandas as pd
from pandas_datareader import data as web
from pandas import Series, DataFrame
import datetime
from operator import itemgetter
# edit below for 2 dates you wish to calculate:
start = datetime.datetime(2014, 7, 15)
end = datetime.datetime(2017, 7, 25)
stocks = ('AAPL', 'GOOGL', 'YHOO', 'MSFT', 'AMZN', 'DAI')
# store all the dataframes in a list
data = []
for eq in stocks:
data.append(web.DataReader(eq, 'google', start, end))
# print required fields from each dataframe
for df in data:
print (df.ix[start]['Close'])/(df.ix[end]['Close'])
Output:
0.624067042032
0.612014075932
0.613225417599
0.572179539021
0.340850298595
1.28323537643
Thanks to the other answers, they both helped lot. This is my final improved script thanks to that help:
import numpy as np
import pandas as pd
from pandas_datareader import data as web
from pandas import Series, DataFrame
import datetime
from operator import itemgetter
# edit below for 2 dates you wish to calculate:
start = datetime.datetime(2014, 7, 15)
end = datetime.datetime(2017, 7, 25)
stocks = ('AAPL', 'GOOGL', 'YHOO', 'MSFT', 'AMZN', 'DAI')
dict1 = {}
for eq in stocks:
df = web.DataReader(eq, 'google', start, end)
k = ((df.loc[start]['Close'])/(df.loc[end]['Close']))
dict1 [eq] = k
out = sorted(dict1.items(), key=itemgetter(1), reverse = True)
for tick , change in out:
print (tick,"\t", change)
I am trying to annotate my plot with part of a dataframe. However, the time 00:00:00 is appearing in all the row labels. Is there a clean way to remove them since my data is daily in frequency? I have tried the normalize function but that doesn't remove the time; it just zeroes the time.
Here is what the issue looks like and the sample code to reproduce the issue.
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from pandas.tools.plotting import table
# Setup of mock data
date_range = pd.date_range('2014-01-01', '2015-01-01', freq='MS')
df = pd.DataFrame({'Values': np.random.rand(0, 10, len(date_range))}, index=date_range)
# The plotting of the table
fig7 = plt.figure()
ax10 = plt.subplot2grid((1, 1), (0, 0))
table(ax10, np.round(df.tail(5), 2), loc='center', colWidths=[0.1] * 2)
fig7.show()
Simply access the .date attribute of the DateTimeIndex so that every individual element of your index would be represented in datetime.date format.
The default DateTimeIndex format is datetime.datetime which gets defined automatically even if you didn't explicitly define your index that way before.
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from pandas.tools.plotting import table
np.random.seed(42)
# Setup of mock data
date_range = pd.date_range('2014-01-01', '2015-01-01', freq='MS')
df = pd.DataFrame({'Values': np.random.rand(len(date_range))}, date_range)
df.index = df.index.date # <------ only change here
# The plotting of the table
fig7 = plt.figure()
ax10 = plt.subplot2grid((1, 1), (0, 0))
table(ax10, np.round(df.tail(5), 2), loc='center', colWidths=[0.1] * 2)
fig7.show()