I have been successfully replacing all the numbers in my dataframe with their current positive streak number. However, I find my code to be quite messy as I am doing it column by column and manually mentioning the column names each time. Can anyone suggest a more efficient way to achieve this with just a few lines of code?
If you have any ideas on how to simplify my code, please share them!
df = pd.DataFrame([[9, 5, 2], [-2, 6, -4], [-5, 1, -1], [9, 6, -5], [7, -1, -3], [6, -4, 1],
[2, -9, 3]],
columns=['A', 'B', 'C'], index=[1, 2, 3, 4, 5, 6, 7])
def streaks(df, col):
sign = np.sign(df[col])
s = sign.groupby((sign!=sign.shift()).cumsum()).cumsum()
return df.assign(A=s.where(s>0, 0.0).abs())
df = streaks(df, 'A')
def streaks(df, col):
sign = np.sign(df[col])
s = sign.groupby((sign!=sign.shift()).cumsum()).cumsum()
return df.assign(B=s.where(s>0, 0.0).abs())
df = streaks(df, 'B')
def streaks(df, col):
sign = np.sign(df[col])
s = sign.groupby((sign!=sign.shift()).cumsum()).cumsum()
return df.assign(C=s.where(s>0, 0.0).abs())
df = streaks(df, 'C')