Develop Reference

Python Return Statement Not Providing Expected Results

Just attempting to return values from a defined function. When calling the function first and attempting to print the return values I receive "[variable] not defined". However, if I run "print(qb_stat_filler())" it prints the results in a tuple. I need the individual variables returned to use in a separate function.
For Example
print(qb_stat_filler())
outputs: (0, 11, 24, 24.2024, 39.1143, 293.0, 1.9143000000000001, 0.2262, 97.84333355313255)
but when trying
qb_stat_filler()
print(cmp_avg)
print(att_avg)
outputs: NameError: name 'cmp_avg' is not defined
Process finished with exit code 1
I've tried establishing the variables outside of the function, then passing and returning them and that did not work either. Any thoughts?
def qb_stat_filler():
n_input = input('Player name: ')
t_input = input('Players team: ')
loc_input = input('H or #: ')
o_input = input('Opponent: ')
# convert index csv to dictionary of player values
q = pd.read_csv('Models\\QB Indexes\\QBname.csv')
q = q[['Player', 'Num']]
qb_dict = dict(q.values)
name = qb_dict.get('{}'.format(n_input))
t = pd.read_csv('Models\\QB Indexes\\Tmname.csv')
t = t[['Tm', 'Num']]
tm_dict = dict(t.values)
team = tm_dict.get('{}'.format(t_input))
loc = 0
if loc_input == '#':
loc = 0
elif loc_input == 'H':
loc = 1
z = pd.read_csv('Models\\QB Indexes\\Oppname.csv')
z = z[['Opp', 'Num']]
opp_dict = dict(z.values)
opp = opp_dict.get('{}'.format(o_input))
*there are several lines of code here that involve SQL
queries and data cleansing*
cmp_avg = (cmp_match + cmpL4) / 2
att_avg = (patt_match + pattL4) / 2
pyds_avg = (py_match + pydsL4) / 2
ptd_avg = (ptdL4 + ptd_match) / 2
int_avg = (intL4 + int_match) / 2
qbr_avg = (qbr_match + qbrL4) / 2
return name, team, opp, cmp_avg, att_avg, pyds_avg, ptd_avg,
int_avg, qbr_avg
qb_stat_filler()

You might consider:
def qb_stat_filler():
stats = {}
...
stats['name'] = name
z = z[['Opp', 'Num']]
opp_dict = dict(z.values)
stats['opp'] = opp_dict.get('{}'.format(o_input))
...
stats['cmp_avg'] = (cmp_match + cmpL4) / 2
stats['att_avg'] = (patt_match + pattL4) / 2
stats['pyds_avg'] = (py_match + pydsL4) / 2
stats['ptd_avg'] = (ptdL4 + ptd_match) / 2
stats['int_avg'] = (intL4 + int_match) / 2
stats['qbr_avg'] = (qbr_match + qbrL4) / 2
return stats
...
stats = qb_stat_filler()
print(stats['cmp_avg'])

ValueError: substring not found on lip reading code

This is what I have gotten while trying to run step 3 of this source code:
https://github.com/carykh/lazykh
Error:
Traceback (most recent call last):
File "C:\Users\User\Desktop\lazykh-main\code\scheduler.py", line 93, in
OS_nextIndex = originalScript.index(wordString,OS_IndexAt)+len(wordString)
ValueError: substring not found
Code:
import argparse
import os.path
import json
import numpy as np
import random
def addPhoneme(p, t):
global prevPhoneme
global f
if p != prevPhoneme:
strings[4] += (str.format('{0:.3f}', t)+",phoneme,"+p+"\n")
prevPhoneme = p
def pickNewPose(t):
global pose
global prevPose
global POSE_COUNT
global prevPhoneme
global f
newPose = -1
while newPose == -1 or newPose == pose or newPose == prevPose:
newPose = int(random.random()*POSE_COUNT)
prevPose = pose
pose = newPose
strings[3] += (str.format('{0:.3f}', t)+",pose,"+str(pose)+"\n")
prevPhoneme = "na"
strings = [""]*5
POSE_COUNT = 5
emotions = {}
emotions["explain"] = 0
emotions["happy"] = 1
emotions["sad"] = 2
emotions["angry"] = 3
emotions["confused"] = 4
emotions["rq"] = 5
mouthList = [["aa","a"],["ae","a"],["ah","a"],["ao","a"],["aw","au"],
["ay","ay"],["b","m"],["ch","t"],["d","t"],["dh","t"],
["eh","a"],["er","u"],["ey","ay"],["f","f"],["g","t"],
["hh","y"],["ih","a"],["iy","ay"],["jh","t"],["k","t"],
["l","y"],["m","m"],["n","t"],["ng","t"],["ow","au"],
["oy","ua"],["p","m"],["r","u"],["s","t"],["sh","t"],
["t","t"],["th","t"],["uh","u"],["uw","u"],["v","f"],
["w","u"],["y","y"],["z","t"],["zh","t"],
["oov","m"]] # For unknown phonemes, the stick figure will just have a closed mouth ("mmm")
mouths = {}
for x in mouthList:
mouths[x[0]] = x[1]
ENDING_PHONEME = "m"
STOPPERS = [",",";",".",":","!","?"]
parser = argparse.ArgumentParser(description='blah')
parser.add_argument('--input_file', type=str, help='the script')
args = parser.parse_args()
INPUT_FILE = args.input_file
f = open(INPUT_FILE+".txt","r+")
originalScript = f.read()
f.close()
f = open(INPUT_FILE+".json","r+")
fileData = f.read()
f.close()
data = json.loads(fileData)
WORD_COUNT = len(data['words'])
pose = -1
prevPose = -1
prevPhoneme = "na"
emotion = "0"
pararaph = 0
image = 0
OS_IndexAt = 0
pickNewPose(0)
strings[1] += "0,emotion,0\n"
strings[0] += "0,paragraph,0\n"
strings[2] += "0,image,0\n"
strings[4] += "0,phoneme,m\n"
for i in range(WORD_COUNT):
word = data['words'][i]
if "start" not in word:
continue
wordString = word["word"]
timeStart = word["start"]
OS_nextIndex = originalScript.index(wordString,OS_IndexAt)+len(wordString)
if "<" in originalScript[OS_IndexAt:]:
tagStart = originalScript.index("<",OS_IndexAt)
tagEnd = originalScript.index(">",OS_IndexAt)
if OS_nextIndex > tagStart and tagEnd >= OS_nextIndex:
OS_nextIndex = originalScript.index(wordString,tagEnd)+len(wordString)
nextDigest = originalScript[OS_IndexAt:OS_nextIndex]
if "\n" in nextDigest and data['words'][i-1]['case'] != 'not-found-in-audio' and (prevPhoneme == "a" or prevPhoneme == "f" or prevPhoneme == "u" or prevPhoneme == "y"):
addPhoneme("m", data['words'][i-1]["end"])
"""print(wordString)
print(str(OS_IndexAt)+", "+str(OS_nextIndex))
print(nextDigest)
print("")"""
pickedPose = False
for stopper in STOPPERS:
if stopper in nextDigest:
pickNewPose(timeStart)
pickedPose = True
if "<" in nextDigest:
leftIndex = nextDigest.index("<")+1
rightIndex = nextDigest.index(">")
emotion = emotions[nextDigest[leftIndex:rightIndex]]
strings[1] += (str.format('{0:.3f}', timeStart)+",emotion,"+str(emotion)+"\n")
prevPhoneme = "na"
if "\n\n" in nextDigest:
pararaph += 1
image += 1 # The line of the script advances 2 lines whenever we hit a /n/n.
strings[0] += (str.format('{0:.3f}', timeStart)+",paragraph,"+str(pararaph)+"\n")
prevPhoneme = "na"
if "\n" in nextDigest:
image += 1
strings[2] += (str.format('{0:.3f}', timeStart)+",image,"+str(image)+"\n")
prevPhoneme = "na"
if not pickedPose:
pickNewPose(timeStart) # A new image means we also need to have a new pose
phones = word["phones"]
timeAt = timeStart
for phone in phones:
timeAt += phone["duration"]
phoneString = phone["phone"]
if phoneString == "sil":
truePhone = "m"
else:
truePhone = mouths[phoneString[:phoneString.index("_")]]
if len(truePhone) == 2:
addPhoneme(truePhone[0], timeAt-phone["duration"])
addPhoneme(truePhone[1], timeAt-phone["duration"]*0.5)
else:
addPhoneme(truePhone, timeAt-phone["duration"])
OS_IndexAt = OS_nextIndex
f = open(INPUT_FILE+"_schedule.csv","w+")
for i in range(len(strings)):
f.write(strings[i])
if i < len(strings)-1:
f.write("SECTION\n")
f.flush()
f.close()
print(f"Done creating schedule for {INPUT_FILE}.")

The
ValueError: substring not found
occurs when you try to find the index of a substring in a string which does not contain it in the specified (or default) section, using the index function.
The index method takes 3 parameters:
value
start
end
and it searches for the value between start and end.
So, the error occurred because the substring was not found in the section where it was searched for. The line of
OS_nextIndex = originalScript.index(wordString,tagEnd)+len(wordString)
searches for wordString, starting from tagEnd and searches for the likes of
<span>yourwordstring</span>
, but in your case it was not found. You can do one of the following to solve the issue:
you can fix your input if it should always have a match for the search
you can handle the error when the index throws the error
you can use find instead, see https://bobbyhadz.com/blog/python-valueerror-substring-not-found
Note that find also has three parameters, as you can read from https://www.w3schools.com/python/ref_string_find.asp

splitting names by counting commas gives value error

I have been using this code for this process for around six months and now it is throwing a ValueError: Columns must be same length as key. I haven't changed anything so I am not sure what could be wrong. Basically, I am pulling data from my system and it has names formatted like this FN1, FN2 LN1, LN2 and I need the names to be FN1 LN1 and FN2 LN2. The code runs fine until this last line.
df_gs_recruiter[[f'Recruiter_{j}']] = df_gs_recruiter[f'FN{j}'] + ' ' + df_gs_recruiter[f'LN{j}']
Sample of the data in:
Job ID
Recruiters
0
729538
Bonnie,Tina Smith,Matthews
1
720954
Cindy,Ken Harris,Walsh
2
720954
Cindy,Ken Harris,Walsh
3
721061
Cindy,Ken Harris,Walsh
import numpy as np
num_comma = df_gs_recruiter.Recruiters.str.count(',')
r_min = num_comma.min()
r_max = num_comma.max()
print(r_min,r_max)
df_gs_recruiter[['FN','LN']] = df_gs_recruiter.Recruiters.str.extract('(.*) (.*)',expand=True)
for i in range(len(df_gs_recruiter)):
r = df_gs_recruiter.loc[i,'Recruiters'].count(',')
if r/2 == 6:
df_gs_recruiter[['FN1','FN2','FN3','FN4','FN5', 'FN6', 'FN7']] = df_gs_recruiter.FN.str.extract('(.*),(.*),(.*),(.*),(.*),(.*),(.*)',expand=True)
df_gs_recruiter[['LN1','LN2','LN3','LN4','LN5', 'LN6', 'LN7']] = df_gs_recruiter.LN.str.extract('(.*),(.*),(.*),(.*),(.*),(.*),(.*)',expand=True)
elif r/2 == 5:
df_gs_recruiter[['FN1','FN2','FN3','FN4','FN5', 'FN6']] = df_gs_recruiter.FN.str.extract('(.*),(.*),(.*),(.*),(.*),(.*)',expand=True)
df_gs_recruiter[['LN1','LN2','LN3','LN4','LN5', 'LN6']] = df_gs_recruiter.LN.str.extract('(.*),(.*),(.*),(.*),(.*),(.*)',expand=True)
elif r/2 == 4:
df_gs_recruiter[['FN1','FN2','FN3','FN4','FN5']] = df_gs_recruiter.FN.str.extract('(.*),(.*),(.*),(.*),(.*)',expand=True)
df_gs_recruiter[['LN1','LN2','LN3','LN4','LN5']] = df_gs_recruiter.LN.str.extract('(.*),(.*),(.*),(.*),(.*)',expand=True)
elif r/2 == 3:
df_gs_recruiter[['FN1','FN2','FN3','FN4']] = df_gs_recruiter.FN.str.extract('(.*),(.*),(.*),(.*)',expand=True)
df_gs_recruiter[['LN1','LN2','LN3','LN4']] = df_gs_recruiter.LN.str.extract('(.*),(.*),(.*),(.*)',expand=True)
elif r/2 == 2:
df_gs_recruiter[['FN1','FN2','FN3']] = df_gs_recruiter.FN.str.extract('(.*),(.*),(.*)',expand=True)
df_gs_recruiter[['LN1','LN2','LN3']] = df_gs_recruiter.LN.str.extract('(.*),(.*),(.*)',expand=True)
elif r/2 == 1:
df_gs_recruiter[['FN1','FN2']] = df_gs_recruiter.FN.str.extract('(.*),(.*)',expand=True)
df_gs_recruiter[['LN1','LN2']] = df_gs_recruiter.LN.str.extract('(.*),(.*)',expand=True)
df_gs_recruiter.loc[i,'num'] = r/2 + 1
df_gs_recruiter.loc[i,'num'].astype(np.int8)
if df_gs_recruiter.loc[i,'num'] < 1.5:
df_gs_recruiter.loc[i,'FN0'] = df_gs_recruiter.loc[i,'FN']
df_gs_recruiter.loc[i,'LN0'] = df_gs_recruiter.loc[i,'LN']
else:
df_gs_recruiter.loc[i,'FN0'] = 'null'
df_gs_recruiter.loc[i,'LN0'] = 'null'
df_gs_recruiter.replace('null', np.nan, inplace=True)
for j in range(0,int(r_max/2)+2):
df_gs_recruiter[[f'Recruiter_{j}']] = df_gs_recruiter[f'FN{j}'] + ' ' + df_gs_recruiter[f'LN{j}']
Expected outcome:
0 4
Then this next part runs and shows the outcome.
for col in df_gs_recruiter.columns:
if 'Recruiter_' not in col and 'Job ID' not in col:
df_gs_recruiter.drop([f'{col}'],axis=1, inplace=True)
df_gs_recruiter
Expected outcome is:
Job ID
Recruiter_0
Recruiter_1
Recruiter_2
Recruiter_3
0
729538
NaN
Bonnie Smith
Tina Matthews
NaN
1
720954
NaN
Cindy Harris
Ken Walsh

How can I display max number of loses from this dataframe in Pandas?

I wrote a webscraper which is downloading table tennis data. There is info about players, match score etc. I would like to display players which lost the most matches per day. I've created data frame and I would like to sum p1_status and p2_status, then I would like to display Surname and number of loses next to player.
https://gyazo.com/19c70e071db78071e83045bfcea0e772
Here is my code:
s = Service("D:/setka/chromedriver.exe")
option = webdriver.ChromeOptions()
driver = webdriver.Chrome(service=s)
hall = 10
num =1
filename = "C:/Users/filip/result2.csv"
f=open(filename,"w")
headers = "p1_surname, p1_name, p1_score, p2_surname, p2_name, p2_score, p1_status, p2_status \n"
f.write(headers)
while hall <= 10:
for period in [1]:
url = 'https://tabletennis.setkacup.com/en/schedule?date=2021-12-04&hall=' + \
str(hall) + '&' + 'period=' + str(period)
driver.get(url)
time.sleep(5)
divs = driver.find_elements(By.CSS_SELECTOR, "div.score-result")
for div in divs:
data = div.text.split()
#print(data)
if(num % 2) == 0:
f.write(str(data[0]) + "," + str(data[1]) + "," + str(data[2] + "," + "\n"))
else:
f.write(str(data[0]) + "," + str(data[1]) + "," + str(data[2] + ","))
num = num +1
hall =hall + 1
f.close()
df_results=pd.read_csv('C:/Users/filip/result2.csv', sep = r',',
skipinitialspace = True)
df_results.reset_index(drop=True, inplace=True)
df_results.loc[df_results['p1_score'] > df_results['p2_score'], ['p1_status','p2_status']] = ['won','lost']
df_results.loc[df_results['p1_score'] < df_results['p2_score'], ['p1_status','p2_status']] = ['lost','won']
df_results.loc[df_results['p1_score'] == df_results['p2_score'], ['p1_status','p2_status']] = ['not played','not played']
df_results.loc[((df_results['p1_score'] < 3) & (df_results['p1_score']!=0) & (df_results['p2_score'] <3) & (df_results['p2_score']!=0)), ['p1_status','p2_status']] = ['inplay','inplays']
df_results.loc[df_results['p1_status'] != df_results['p2_status'], ['match_status']] = ['finished']
df_results.loc[df_results['p1_status'] == df_results['p2_status'], ['match_status']] = ['not played']
df_results.loc[((df_results['p1_status'] =='inplay') & (df_results['p2_status']=='inplays')), ['match_status']] = ['inplay']
df_results = df_results.dropna(axis=1)
df_results.head(30)

Split your dataframe in 2 parts (p1_, p2_) to count defeats of each player then merge them:
Setup a MRE:
df = pd.DataFrame({'p1_surname': list('AABB'), 'p2_surname': list('CDCD'),
'p1_status': list('LWWW'), 'p2_status': list('WLLL')})
print(df)
# Output:
p1_surname p2_surname p1_status p2_status
0 A C L W
1 A D W L
2 B C W L
3 B D W L
>>> pd.concat([
df.filter(like='p1_').set_index('p1_surname')['p1_status'].eq('L').rename('loses'),
df.filter(like='p2_').set_index('p2_surname')['p2_status'].eq('L').rename('loses')]) \
.groupby(level=0).sum().rename_axis('surname').reset_index()
surname loses
0 A 1
1 B 0
2 C 1
3 D 2

Single list.count instead of multiple

Im parsed list of crew witch one looks like:
20;mechanic;0;68
21;cook;0;43
22;scientist;0;79
23;manager;1;65
24;mechanic;1;41
etc
And now I'm trying to figure out how to count number of workers who have 60 or more stamina( the last element in each employee )
There is my code:
with open('employee.txt', 'r') as employee_list:
count = 0
for employee in employee_list.readlines():
employee_data = employee.rstrip().split(';')
if int(employee_data[3]) >= 60:
count += 1
print(count)
Print from terminal:
1
2
3
...
90
And there is the right answer I think, but is there anyway to get only one 'total' count, not a 90ty strings ?

Just print one line after the loop is done.
with open('employee.txt', 'r') as employee_list:
count = 0
for employee in employee_list.readlines():
employee_data = employee.rstrip().split(';')
if int(employee_data[3]) >= 60:
count += 1
print(count)
But I would also recommend using pandas for data manipulation. For example:
df = pd.read_csv('employee.txt', sep=';')
df.columns = ['col1', 'col2', 'col3', 'stamina']
Then just filter and get the size:
df[df.stamina >= 60].size

So after a day of thinking I wrote this and get right answer ( maybe someone will find this helpful):
def total_resist_count():
# with open('employee.txt', 'r') as employee_list:
employee_list = [input() for i in range(120)]
candidates = []
for employee in employee_list:
employee_data = employee.rstrip().split(';')
if int(employee_data[3]) >= 60:
candidates.append(employee_data)
return candidates
required_professionals = {
'computers specialist': 5,
'cook': 3,
'doctor': 5,
'electrical engineer': 4,
'manager': 1,
'mechanic': 8,
'scientist': 14
}
expedition_total = 40
female_min = 21
male_min = 12
def validate_solution(cur_team, num_females, num_males):
global expedition_total, female_min, male_min
if sum(cur_team) != expedition_total or num_females < female_min or num_males < male_min:
return False
num_of_free_vacancies = 0
for k in required_professionals:
num_of_free_vacancies += required_professionals[k]
if num_of_free_vacancies > 0:
return False
return True
TEAM = None
def backtrack(candidates, cur_team, num_females, num_males):
global required_professionals, expedition_total, TEAM
if sum(cur_team) > expedition_total or TEAM is not None:
return
if validate_solution(cur_team, num_females, num_males):
team = []
for i, used in enumerate(cur_team):
if used == 1:
team.append(candidates[i])
TEAM = team
return
for i in range(len(candidates)):
if cur_team[i] == 0 and required_professionals[candidates[i][1]] > 0:
cur_team[i] = 1
required_professionals[candidates[i][1]] -= 1
if candidates[i][2] == '1':
backtrack(candidates, cur_team, num_females, num_males + 1)
else:
backtrack(candidates, cur_team, num_females + 1, num_males)
required_professionals[candidates[i][1]] += 1
cur_team[i] = 0
if __name__ == '__main__':
ec = decode_fcc_message()
candidates = total_resist_count(ec)
cur_team = [0] * len(candidates)
backtrack(candidates, cur_team, 0, 0)
s = ""
for t in TEAM:
s += str(t[0]) + ';'
print(s)