I have a pandas.dataframe, and I want to select certain data by some rules.
The following codes generate the dataframe
import datetime
import pandas as pd
import numpy as np
today = datetime.date.today()
dates = list()
for k in range(10):
a_day = today - datetime.timedelta(days=k)
dates.append(np.datetime64(a_day))
np.random.seed(5)
df = pd.DataFrame(np.random.randint(100, size=(10, 3)),
columns=('other1', 'actual', 'other2'),
index=['{}'.format(i) for i in range(10)])
df.insert(0, 'dates', dates)
df['err_m'] = np.random.rand(10, 1)*0.1
df['std'] = np.random.rand(10, 1)*0.05
df['gain'] = np.random.rand(10, 1)
Now, I want select by the following rules:
1. compute the sum of 'err_m' and 'std', then sort the df so that the sum is descending
2. from the result of step 1, select the part where 'actual' is > 50
Thanks
Create a new column and then sort by this one:
df['errsum'] = df['err_m'] + df['std']
# Return a sorted dataframe
df_sorted = df.sort('errsum', ascending = False)
Select the lines you want
# Create an array with True where the condition is met
selector = df_sorted['errsum'] > 50
# Return a view of sorted_dataframe with only the lines you want
df_sorted[selector]
Related
I have a list of DataFrames with equal length of columns and rows but different values, such as
data = [df1, df2,df3.... dfn] .
How can I apply a function function on each dataframe in the list data? I used following code but it doe not work
data = [df1, def2,df3.... dfn]
def maxloc(data):
data['loc_max'] = np.zeros(len(data))
for i in range(1,len(data)-1): #from the second value on
if data['q_value'][i] >= data['q_value'][i-1] and data['q_value'][i] >= data['q_value'][i+1]:
data['loc_max'][i] = 1
return data
df_list = [df.pipe(maxloc) for df in data]
Seems to me the problem is in your maxloc() function as this code works.
I added also the maximum value in the return of maxloc.
from random import randrange
import pandas as pd
def maxloc(data_frame):
max_index = data_frame['Value'].idxmax(0)
maximum = data_frame['Value'][max_index]
return max_index, maximum
# create test list of data-frames
data = []
for i in range(5):
temp = []
for j in range(10):
temp.append(randrange(100))
df = pd.DataFrame({'Value': temp}, index=(range(10)))
data.append(df)
df_list = [df.pipe(maxloc) for df in data]
for i, (index, value) in enumerate(df_list):
print(f"Data-frame {i:02d}: maximum = {value} at position {index}")
Have a large pandas DataFrame of 1m rows. I want to perform a calculation on every item and create a new DataFrame from it.
The way I'm currently doing it is crazily slow. Any thoughts on how I might improve the efficiency?
# Create some random data in a DataFrame
import pandas as pd
import numpy as np
dfData = pd.DataFrame(np.random.randint(0,1000,size=(100, 10)), columns=list('ABCDEFGHIJ'))
# Key values
colTotals = dfData.sum(axis=0)
rowTotals = dfData.sum(axis=1)
total = dfData.values.sum()
dfIdx = pd.DataFrame()
for respId, row in dfData.iterrows():
for scores in row.iteritems():
colId = scores[0]
score = scores[1]
# Do the calculation
idx = (score / colTotals[colId]) * (total / rowTotals[respId]) * 100
dfIdx.loc[respId, colId] = idx
I think this is the logic of your code
dfData.div(colTotals).mul((total / rowTotals) * 100, 0)
I have an hourly time series data (say df with date/time and value columns) where I want to:
Step 1: Remove the top 5 percentile of each day
Step 2: Get the max(Step 1)for each day
Step 3: Get the mean(Step 2) for each month
Here is what I have tried to implement the above logic:
step_1 = df.resample('D').apply(lambda x: x<x.quantile(0.95))
step_2 = step_1.resample('D').max()
step_3 = step_2.resample('M').mean()
Even though I do not get any code error, the generated output is different to the expected result based on the above 3 steps (I always get a constant value)
Any help will be appreciated.
You are almost there. Your step_1 is a series of booleans with the same index as the original data, you can use it to filter your DataFrame, thus:
step_1 = df.resample('D').apply(lambda x: x<x.quantile(0.95))
step_2 = df[step_1].resample('D').max()
step_3 = step_2.resample('M').mean()
Your first step is a boolean mask, so you need to add an additional step:
import numpy as np
import pandas as pd
df = pd.DataFrame(np.random.randn(1000), index=pd.date_range(start='1/1/2019', periods=1000, freq='H'), columns=['my_data'])
mask = df.resample('D').apply(lambda x: x < x.quantile(.95))
step_1 = df[mask]
step_2 = df.resample('D').max()
step_3 = df.resample('M').mean()
I'am trying to calculate 33 stock betas and write them to dataframe.
Unfortunately, I have an error in my code:
cannot concatenate object of type ""; only pd.Series, pd.DataFrame, and pd.Panel (deprecated) objs are vali
import pandas as pd
import numpy as np
stock1=pd.read_excel(r"C:\Users\Кир\Desktop\Uni\Master\Nasdaq\Financials 11.05\Nasdaq last\clean data\01.xlsx", '1') #read second sheet of excel file
stock2=pd.read_excel(r"C:\Users\Кир\Desktop\Uni\Master\Nasdaq\Financials 11.05\Nasdaq last\clean data\01.xlsx", '2') #read second sheet of excel file
stock2['stockreturn']=np.log(stock2.AdjCloseStock / stock2.AdjCloseStock.shift(1)) #stock ln return
stock2['SP500return']=np.log(stock2.AdjCloseSP500 / stock2.AdjCloseSP500.shift(1)) #SP500 ln return
stock2 = stock2.iloc[1:] #delete first row in dataframe
betas = pd.DataFrame()
for i in range(0,(len(stock2.AdjCloseStock)//52)-1):
betas = betas.append(stock2.stockreturn.iloc[i*52:(i+1)*52].cov(stock2.SP500return.iloc[i*52:(i+1)*52])/stock2.SP500return.iloc[i*52:(i+1)*52].cov(stock2.SP500return.iloc[i*52:(i+1)*52]))
My data looks like weekly stock and S&P index return for 33 years. So the output should have 33 betas.
I tried simplifying your code and creating an example. I think the problem is that your calculation returns a float. You want to make it a pd.Series. DataFrame.append takes:
DataFrame or Series/dict-like object, or list of these
np.random.seed(20)
df = pd.DataFrame(np.random.randn(33*53, 2),
columns=['a', 'b'])
betas = pd.DataFrame()
for year in range(len(df['a'])//52 -1):
# Take some data
in_slice = pd.IndexSlice[year*52:(year+1)*52]
numerator = df['a'].iloc[in_slice].cov(df['b'].iloc[in_slice])
denominator = df['b'].iloc[in_slice].cov(df['b'].iloc[in_slice])
# Do some calculations and create a pd.Series from the result
data = pd.Series(numerator / denominator, name = year)
# Append to the DataFrame
betas = betas.append(data)
betas.index.name = 'years'
betas.columns = ['beta']
betas.head():
beta
years
0 0.107669
1 -0.009302
2 -0.063200
3 0.025681
4 -0.000813
I am defining a function that is being applied to every row in my Data Frame that counts unique codes in a the column "Code" for every id in the set. The code I have works, but it is incredibly slow and I am using a large data set. I am looking for a different approach that speed up the operation.
from datetime import timedelta as td
import pandas as pd
df['Trailing_12M'] = df['Date'] - td(365) #current date - 1 year as new column
def Unique_Count(row):
"""Creating a new df for each id and returning unique count to every row in original df"""
temp1 = np.array(df['ID'] == row['ID'])
temp2 = np.array(df['Date'] <= row['Date'])
temp3 = np.array(df['Date'] >= row['Trailing_12M'])
temp4 = np.array(temp1 & temp2 & temp3)
df_Unique_Code_Count = np.array(df[temp4].Code.nunique())
return df_Unique_Code_Count
df['Unique_Code_Count'] = df.apply(Unique_Count, axis=1)