I need help to make the snippet below. I need to merge two files and performs computation on matched lines
I have oldFile.txt which contains old data and newFile.txt with an updated sets of data.
I need to to update the oldFile.txt based on the data in the newFile.txt and compute the changes in percentage. Any idea will be very helpful. Thanks in advance
from collections import defaultdict
num = 0
data=defaultdict(int)
with open("newFile.txt", encoding='utf8', errors='ignore') as f:
for line in f:
grp, pname, cnt, cat = line.split(maxsplit=3)
data[(pname.strip(),cat.replace('\n','').strip(),grp,cat)]+=int(cnt)
sorteddata = sorted([[k[0],v,k[1],k[2]] for k,v in data.items()], key=lambda x:x[1], reverse=True)
for subl in sorteddata[:10]:
num += 1
line = " ".join(map(str, subl))
print ("{:>5} -> {:>}".format(str(num), line))
with open("oldFile.txt", 'a', encoding='utf8', errors='ignore') as l:
l.write(" ".join(map(str, subl)) + '\n')
oldFile.txt
#col1 #col2 #col3 #col4
1,396 c15e89f2149bcc0cbd5fb204 4 HUH_Token (HUH)
279 9e4d81c8fc15870b15aef8dc 3 BABY BNB (BBNB)
231 31b5c07636dab8f0909dbd2d 6 Buff Unicorn (BUFFUN...)
438 1c6bc8e962427deb4106ae06 8 Charge (Charge)
2,739 6ea059a29eccecee4e250414 2 MAXIMACASH (MAXCAS...)
newFile.txt #-- updated data with additional lines not found in oldFile.txt
#col1 #col2 #col3 #col4
8,739 6ea059a29eccecee4e250414 60 MAXIMACASH (MAXCAS...)
138 1c6bc8e962427deb4106ae06 50 Charge (Charge)
860 31b5c07636dab8f0909dbd2d 40 Buff Unicorn (BUFFUN...)
200 9e4d81c8fc15870b15aef8dc 30 BABY BNB (BBNB) #-- not found in the oldFile.txt
20 5esdsds2sd15870b15aef8dc 30 CharliesAngel (CA)
1,560 c15e89f2149bcc0cbd5fb204 20 HUH_Token (HUH)
Need Improvement: #-- With additional columns (col5, col6) and sorted based on (col3) values
#col1 #col2 #col3 #col4 #col5 (oldFile-newFile) #col6 (oldFile-newFile)
8,739 6ea059a29eccecee4e250414 62 MAXIMACASH (MAXCAS...) 2900.00 % (col3 2-60) 219.06 % (col1 2,739-8,739)
138 1c6bc8e962427deb4106ae06 58 Charge (Charge) 625.00 % (col3 8-50) -68.49 % (col1 438-138)
860 31b5c07636dab8f0909dbd2d 46 Buff Unicorn (BUFFUN...) 566.67 % (col3 6-40) 272.29 % (col1 231-860)
200 9e4d81c8fc15870b15aef8dc 33 BABY BNB (BBNB) 900.00 % (col3 3-30) -28.32 % (col1 279-200)
20 5esdsds2sd15870b15aef8dc 30 CharliesAngel (CA) 0.00 % (col3 0-30) 20.00 % (col1 0-20)
1,560 c15e89f2149bcc0cbd5fb204 24 HUH_Token (HUH) 400.00 % (col3 4-20) 11.75 % (col1 1,396-1,560)
Just to give a convtools based alternative solution, where you may find useful pieces:
from convtools import conversion as c
from convtools.contrib.tables import Table
# your percentage change calculation
def c_change(column_name):
return c.if_(
c.and_(
c.col(f"{column_name}_LEFT"),
c.col(f"{column_name}_RIGHT").is_not(None),
),
(
(c.col(f"{column_name}_RIGHT") - c.col(f"{column_name}_LEFT"))
/ c.col(f"{column_name}_LEFT")
* 100.0
).pipe(round, 2),
None,
)
prepare_columns = {
"COLUMN_0": c.col("COLUMN_0").as_type(float),
"COLUMN_2": c.col("COLUMN_2").as_type(float),
}
dialect = Table.csv_dialect(delimiter="\t")
sorted_rows = sorted(
Table.from_csv("tmp1.csv", dialect=dialect)
.update(**prepare_columns)
.join(
Table.from_csv(
"tmp2.csv",
dialect=dialect,
).update(**prepare_columns),
on=["COLUMN_1", "COLUMN_3"],
how="full",
)
.update(
COLUMN_4=c_change("COLUMN_2"),
COLUMN_5=c_change("COLUMN_0"),
COLUMN_2=c.col("COLUMN_2_RIGHT"),
COLUMN_0=c.col("COLUMN_0_RIGHT"),
)
.take(
"COLUMN_0",
"COLUMN_1",
"COLUMN_2",
"COLUMN_3",
"COLUMN_4",
"COLUMN_5",
)
.into_iter_rows(tuple),
key=lambda row: row[2],
reverse=True,
)
Table.from_rows(sorted_rows).into_csv("tmp_result.csv", dialect=dialect)
Results in:
COLUMN_0 COLUMN_1 COLUMN_2 COLUMN_3 COLUMN_4 COLUMN_5
8739.0 6ea059a29eccecee4e250414 60.0 MAXIMACASH (MAXCAS...) 2900.0 219.06
138.0 1c6bc8e962427deb4106ae06 50.0 Charge (Charge) 525.0 -68.49
860.0 31b5c07636dab8f0909dbd2d 40.0 Buff Unicorn (BUFFUN...) 566.67 272.29
200.0 9e4d81c8fc15870b15aef8dc 30.0 BABY BNB (BBNB) 900.0 -28.32
20.0 5esdsds2sd15870b15aef8dc 30.0 CharliesAngel (CA)
1560.0 c15e89f2149bcc0cbd5fb204 20.0 HUH_Token (HUH) 400.0 11.75