Passing column variables into Pandas function - pandas

I wrote a function that explicitly defines which rows of a particular column ('UNEXPLAINED_Sq') to sum in a Pandas df based on two other columns ('REPORTING_DATE', 'WindowEnd').
def sum_scores (row):
s = row['REPORTING_DATE']
e = row['WindowEnd']
s_sum = df.loc[df['REPORTING_DATE'] <= s, 'UNEXPLAINED_Sq'].sum()
e_sum = df.loc[df['REPORTING_DATE'] < e, 'UNEXPLAINED_Sq'].sum()
return (s_sum - e_sum)
df.loc[:, 'UNEXPLAINED_Sq_SUM'] = df.apply(sum_scores, axis=1)
Then I made it more generic so I could pass in a column variable to sum:
def sum_scores_5 (row, c_Name):
s = row['REPORTING_DATE']
e = row['WindowEnd']
s_sum = df.loc[df['REPORTING_DATE'] <= s, df[c_Name]].sum
e_sum = df.loc[df['REPORTING_DATE'] < e, df[c_Name]].sum
return (s_sum - e_sum)
df.loc[:, 'UNEXPLAINED_Sq_SUM'] =df.apply(sum_scores_5, 'UNEXPLAINED_Sq', axis=1)
But returns: TypeError: apply() got multiple values for argument 'axis'
Then I thought I would use a lambda function for the multiple variables
df.loc[:, 'UNEXPLAINED_Sq_SUM'] = df.apply(lambda x: sum_scores_5(x, df['UNEXPLAINED_Sq']), axis=1)
But this returns
KeyError: ('[2.01018345e+13 ...\n 1.67234745e+ 3.02534089e+14] not in index', 'occurred at index 0')​
which i think is because I'm attempting to pass the entire column in to be evaluated at each row.
Snippet of the data is listed below. How can I index the column variable to be summed?
*****Data Table*****
REPORTING_DATE UNEXPLAINED_Sq WindowEnd
2019-02-01 2.010183e+13 2018-08-01
2019-02-04 6.136327e+13 2018-08-04
2019-02-05 1.123688e+13 2018-08-05
2019-02-06 1.253237e+12 2018-08-06
2019-02-07 5.673673e+13 2018-08-07

def sum_scores_5 (row, c_Name):
s = row['REPORTING_DATE']
e = row['WindowEnd']
s_sum = df.loc[df['REPORTING_DATE'] <= s, c_Name].sum()
e_sum = df.loc[df['REPORTING_DATE'] < e, c_Name].sum()
return (s_sum - e_sum)
df.loc[:, 'UNEXPLAINED_Sq_SUM'] = df.apply(lambda x: sum_scores_5(x, 'UNEXPLAINED_Sq'), axis=1)

Related

Capping multiples columns

I found an interesting snippet (vrana95) that caps multiple columns, however this function works on the main "df" as well instead to work only on "final_df". Someone knows why?
def cap_data(df):
for col in df.columns:
print("capping the ",col)
if (((df[col].dtype)=='float64') | ((df[col].dtype)=='int64')):
percentiles = df[col].quantile([0.01,0.99]).values
df[col][df[col] <= percentiles[0]] = percentiles[0]
df[col][df[col] >= percentiles[1]] = percentiles[1]
else:
df[col]=df[col]
return df
final_df=cap_data(df)
As I wanted to cap only a few columns I changed the for loop of the original snippet. It works, but I would to know why this function is working with both dataframes.
cols = ['score_3', 'score_6', 'credit_limit', 'last_amount_borrowed', 'reported_income', 'income']
def cap_data(df):
for col in cols:
print("capping the column:",col)
if (((df[col].dtype)=='float64') | ((df[col].dtype)=='int64')):
percentiles = df[col].quantile([0.01,0.99]).values
df[col][df[col] <= percentiles[0]] = percentiles[0]
df[col][df[col] >= percentiles[1]] = percentiles[1]
else:
df[col]=df[col]
return df
final_df=cap_data(df)

groupby with transform minmax

for every city , I want to create a new column which is minmax scalar of another columns (age).
I tried this an get Input contains infinity or a value too large for dtype('float64').
cols=['age']
def f(x):
scaler1=preprocessing.MinMaxScaler()
x[['age_minmax']] = scaler1.fit_transform(x[cols])
return x
df = df.groupby(['city']).apply(f)
From the comments:
df['age'].replace([np.inf, -np.inf], np.nan, inplace=True)
Or
df['age'] = df['age'].replace([np.inf, -np.inf], np.nan)

Pandas apply function on multiple columns

I am trying to apply a function to every column in a dataframe, when I try to do it on just a single fixed column name it works. I tried doing it on every column, but when I try passing the column name as an argument in the function I get an error.
How do you properly pass arguments to apply a function on a data frame?
def result(row,c):
if row[c] >=0 and row[c] <=1:
return 'c'
elif row[c] >1 and row[c] <=2:
return 'b'
else:
return 'a'
cols = list(df.columns.values)
for c in cols
df[c] = df.apply(result, args = (c), axis=1)
TypeError: ('result() takes exactly 2 arguments (21 given)', u'occurred at index 0')
Input data frame format:
d = {'c1': [1, 2, 1, 0], 'c2': [3, 0, 1, 2]}
df = pd.DataFrame(data=d)
df
c1 c2
0 1 3
1 2 0
2 1 1
3 0 2
You don't need to pass the column name to apply. As you only want to check if values of the columns are in certain range and should return a, b or c. You can make the following changes.
def result(val):
if 0<=val<=1:
return 'c'
elif 1<val<=2:
return 'b'
return 'a'
cols = list(df.columns.values)
for c in cols
df[c] = df[c].apply(result)
Note that this will replace your column values.
A faster way is np.select:
import numpy as np
values = ['c', 'b']
for col in df.columns:
df[col] = np.select([0<=df[col]<=1, 1<df[col]<=2], values, default = 'a')

Time Difference between Time Period and Instant

I have some time periods (df_A) and some time instants (df_B):
import pandas as pd
import numpy as np
import datetime as dt
from datetime import timedelta
# Data
df_A = pd.DataFrame({'A1': [dt.datetime(2017,1,5,9,8), dt.datetime(2017,1,5,9,9), dt.datetime(2017,1,7,9,19), dt.datetime(2017,1,7,9,19), dt.datetime(2017,1,7,9,19), dt.datetime(2017,2,7,9,19), dt.datetime(2017,2,7,9,19)],
'A2': [dt.datetime(2017,1,5,9,9), dt.datetime(2017,1,5,9,12), dt.datetime(2017,1,7,9,26), dt.datetime(2017,1,7,9,20), dt.datetime(2017,1,7,9,21), dt.datetime(2017,2,7,9,23), dt.datetime(2017,2,7,9,25)]})
df_B = pd.DataFrame({ 'B': [dt.datetime(2017,1,6,14,45), dt.datetime(2017,1,4,3,31), dt.datetime(2017,1,7,3,31), dt.datetime(2017,1,7,14,57), dt.datetime(2017,1,9,14,57)]})
I can match these together:
# Define an Extra Margin
M = dt.timedelta(days = 10)
df_A["A1X"] = df_A["A1"] + M
df_A["A2X"] = df_A["A2"] - M
# Match
Bv = df_B .B .values
A1 = df_A .A1X.values
A2 = df_A .A2X.values
i, j = np.where((Bv[:, None] >= A1) & (Bv[:, None] <= A2))
df_C = pd.DataFrame(np.column_stack([df_B .values[i], df_A .values[j]]),
columns = df_B .columns .append (df_A.columns))
I would like to find the time difference between each time period and the time instant matched to it. I mean that
if B is between A1 and A2
then dT = 0
I've tried doing it like this:
# Calculate dt
def time(A1,A2,B):
if df_C["B"] < df_C["A1"]:
return df_C["A1"].subtract(df_C["B"])
elif df_C["B"] > df_C["A2"]:
return df_C["B"].subtract(df_C["A2"])
else:
return 0
df_C['dt'] = df_C.apply(time)
I'm getting "ValueError: Cannot set a frame with no defined index and a value that cannot be converted to a Series"
So, I found two fixes:
You are adding M to the lower value and subtracting from the higher one. Change it to:
df_A['A1X'] = df_A['A1'] - M
df_A['A2X'] = df_A['A2'] + M
You are only passing one row of your dataframe at a time to your time function, so it should be something like:
def time(row):
if row['B'] < row['A1']:
return row['A1'] - row['B']
elif row['B'] > row['A2']:
return row['B'] - row['A2']
else:
return 0
And then you can call it like this:
df_C['dt'] = df_C.apply(time, axis=1) :)

How to use the values of one column to access values in another column?

How to use the values of one column to access values in another
import numpy
impot pandas
numpy.random.seed(123)
df = pandas.DataFrame((numpy.random.normal(0, 1, 10)), columns=[['Value']])
df['bleh'] = df.index.to_series().apply(lambda x: numpy.random.randint(0, x + 1, 1)[0])
so how to access the value 'bleh' for each row?
df.Value.iloc[df['bleh']]
Edit:
Thanks to #ScottBoston. My DF constructor had one layer of [] too much.
The correct answer is:
numpy.random.seed(123)
df = pandas.DataFrame((numpy.random.normal(0, 1, 10)), columns=['Value'])
df['bleh'] = df.index.to_series().apply(lambda x: numpy.random.randint(0, x + 1, 1)[0])
df['idx_int'] = range(df.shape[0])
df['haa'] = df['idx_int'] - df.bleh.values
df['newcol'] = df.Value.iloc[df['haa'].values].values
Try:
df['Value'].tolist()
Output:
[-1.0856306033005612,
0.9973454465835858,
0.28297849805199204,
-1.506294713918092,
-0.5786002519685364,
1.651436537097151,
-2.426679243393074,
-0.42891262885617726,
1.265936258705534,
-0.8667404022651017]
Your dataframe constructor still needs to be fixed.
Are you looking for:
df.set_index('bleh')
output:
Value
bleh
0 -1.085631
1 0.997345
2 0.282978
1 -1.506295
4 -0.578600
0 1.651437
0 -2.426679
4 -0.428913
1 1.265936
7 -0.866740
If so you, your dataframe constructor has as extra set of [] in it.
np.random.seed(123)
df = pd.DataFrame((np.random.normal(0, 1, 10)), columns=['Value'])
df['bleh'] = df.index.to_series().apply(lambda x: np.random.randint(0, x + 1, 1)[0])
columns paramater in dataframe takes a list not a list of list.