Develop Reference

I am outputting an altered tsv file to a new tsv file but the format is wrong

I've been working on this lab project to take in some tsv values of a "grade book" run some calculations, and finally output them to a new report.txt file but whenever I get to the end to print out my report.txt the format of the file doesn't match what I'd expect from a row by row tsv file and is instead a giant list.
So my question is how can I convert my list into a proper line by line tsv like below?
Barrett Edan 70 45 59 F
Bradshaw Reagan 96 97 88 A
Charlton Caius 73 94 80 B
Mayo Tyrese 88 61 36 D
Stern Brenda 90 86 45 C
Averages: midterm1 83.40, midterm2 76.60, final 61.60
My input is commented out in the StudentInfo.tsv= below
My current output is listed below the code.
# TODO: Declare any necessary variables here.
import csv
studentgrades=[]
s_grades=[]
all_grades=[]
all_grades_computed=[]
# TODO: Read a file name from the user and read the tsv file here.
#StudentInfo.tsv= Barrett Edan 70 45 59
# Bradshaw Reagan 96 97 88
# Charlton Caius 73 94 80
# Mayo Tyrese 88 61 36
# Stern Brenda 90 86 45
with open('StudentInfo.tsv', 'r') as file:
studentgrades = csv.reader(file, delimiter='\t')
sgrades=list(studentgrades)
for row in sgrades:
avg2=0
rowstr=' '
for i in row[2:]:
avg2+=int(i)
#print(i)
#print(avg2)
studentavg=float(int(avg2)/len(row[2:]))
if studentavg >= 90:
s_grades.append('A')
elif 80<=studentavg<90:
s_grades.append('B')
elif 70<=studentavg<80:
s_grades.append('C')
elif 60<=studentavg<70:
s_grades.append('D')
else:
s_grades.append('F')
print('{} average: {:.2f}'.format(rowstr.join(row[0:2]), studentavg))
#print('test length',len(row[2:]))
#print(row[2:])
print()
print(s_grades)
print(sgrades)
# for i in s_grades:
# sgrades.append(i)
# print(sgrades)
for i in range(len(s_grades)):
all_grades.append(str(sgrades[i])+str(s_grades[i]))
print(all_grades)
print()
# TODO: Compute student grades and exam averages, then output results to a text file here.
student1=sgrades[0]
student2=sgrades[1]
student3=sgrades[2]
student4=sgrades[3]
student5=sgrades[4]
print('Averages:',end=' ')
midterm1=(int(student1[2])+int(student2[2])+int(student3[2])+int(student4[2])+int(student5[2]))/len(sgrades)
#print(student1[2])
print('midterm1','{:.2f},'.format(midterm1),end=' ')
midterm2=(int(student1[3])+int(student2[3])+int(student3[3])+int(student4[3])+int(student5[3]))/len(sgrades)
#print(student1[3])
print('midterm2','{:.2f},'.format(midterm2),end=' ')
final=(int(student1[4])+int(student2[4])+int(student3[4])+int(student4[4])+int(student5[4]))/len(sgrades)
print('final','{:.2f}'.format(final))
all_grades_computed=['Averages:','midterm1','{:.2f},'.format(midterm1),'midterm2','{:.2f},'.format(midterm2), 'final','{:.2f}'.format(final)]
with open('report.txt', 'w+') as report:
csv_writer=csv.writer(report, delimiter='\t')
csv_writer.writerow(all_grades)
csv_writer.writerow(all_grades_computed)
with open('report.txt','r') as report:
reports=csv.reader(report, delimiter='\t')
reportlist=list(reports)
print(reportlist)
Barrett Edan average: 58.00
Bradshaw Reagan average: 93.67
Charlton Caius average: 82.33
Mayo Tyrese average: 61.67
Stern Brenda average: 73.67
['F', 'A', 'B', 'D', 'C']
[['Barrett', 'Edan', '70', '45', '59'], ['Bradshaw', 'Reagan', '96', '97', '88'], ['Charlton', 'Caius', '73', '94', '80'], ['Mayo', 'Tyrese', '88', '61', '36'], ['Stern', 'Brenda', '90', '86', '45']]
["['Barrett', 'Edan', '70', '45', '59']F", "['Bradshaw', 'Reagan', '96', '97', '88']A", "['Charlton', 'Caius', '73', '94', '80']B", "['Mayo', 'Tyrese', '88', '61', '36']D", "['Stern', 'Brenda', '90', '86', '45']C"]
Averages: midterm1 83.40, midterm2 76.60, final 61.60
[["['Barrett', 'Edan', '70', '45', '59']F", "['Bradshaw', 'Reagan', '96', '97', '88']A", "['Charlton', 'Caius', '73', '94', '80']B", "['Mayo', 'Tyrese', '88', '61', '36']D", "['Stern', 'Brenda', '90', '86', '45']C"], ['Averages:', 'midterm1', '83.40,', 'midterm2', '76.60,', 'final', '61.60']]

Pandas, Python - Assembling a Data Frame with multiple lists from loop

Using loop to collect target data into lists from JSON file. These lists are organized as columns and their values are organized; thus, no manipulation/reorganization is required. Only attaching them horizontally.
#Selecting Data into List
i=1
target = f'{pathway}\calls_{i}.json'
with open(target,'r') as f: #Reading JSON file
data = json.load(f)
specsA=('PreviousDraws',['DrawNumber'])
draw=(glom(data,specsA)) #list type; glom is a package to access nested data in JSON file.
print(draw)
for j in range(0,5):
specsB=('PreviousDraws',['WinningNumbers'],[f'{j}'],['Number'])
number=(glom(data,specsB)) #list type; glom is a package to access nested data in JSON file.
print(number)
#Now assembling lists into a table using pandas
The resulting lists from the code above are as followed below:
#This is from variable draw
[10346, 10345, 10344, 10343, 10342, 10341, 10340, 10339, 10338, 10337, 10336, 10335, 10334, 10333, 10332, 10331, 10330, 10329, 10328, 10327]
#This is from variable number
['22', '9', '4', '1', '1', '14', '5', '3', '2', '8', '2', '1', '4', '9', '4', '4', '3', '13', '7', '14']
['28', '18', '16', '2', '3', '17', '16', '13', '11', '9', '8', '2', '9', '19', '7', '13', '7', '23', '21', '17']
['33', '24', '21', '4', '9', '20', '27', '19', '23', '19', '19', '7', '19', '30', '19', '27', '19', '32', '26', '21']
['35', '30', '28', '11', '21', '23', '33', '26', '35', '37', '27', '12', '20', '31', '22', '34', '22', '36', '27', '25']
['36', '32', '33', '19', '29', '38', '35', '27', '37', '38', '32', '30', '22', '36', '33', '39', '36', '38', '30', '27']
Expected Data Frame table after assembly:
Draw | Number[0] | Number[1] | Number[2] ...
10346 | 22 | 28 |
10345 | 9 | 18 |
10344 | 4 | 16 |
10343 | 1 | 2 |
10342 | 1 | 3 |
My attempt at assembling the table: Organize as dictionary with Series, below:
dct = {'DrawNumbers':pd.Series(draw),
'Index1':pd.Series(number),
'Index2':pd.Series(number),
'Index3':pd.Series(number),
'Index4':pd.Series(number),
'Index5':pd.Series(number)
}
df = pd.DataFrame(dct)
print(df)
Actual result - incorrect due to last list's value being repeated in table's row. So far, only Index5 column is correct, while all index columns are incorrectly represented with index 5's values.
DrawNumbers Index1 Index2 Index3 Index4 Index5
0 10346 36 36 36 36 36
1 10345 32 32 32 32 32
2 10344 33 33 33 33 33
3 10343 19 19 19 19 19
4 10342 29 29 29 29 29
5 10341 38 38 38 38 38
6 10340 35 35 35 35 35
7 10339 27 27 27 27 27
8 10338 37 37 37 37 37
9 10337 38 38 38 38 38
... ... ... ... ... ... ...
Also had tried to change the data type of the number from string to int, but having repeated errors attempted that. Either way, I am stuck and would like to request for assistance.

The problem is that you are overwriting the number variable in the loop, so is no longer available at the end of each iteration, I add a solution adding the column Index in each iteration.
# create an empty dataframe
df = pd.DataFrame()
#Selecting Data into List
i=1
target = f'{pathway}\calls_{i}.json'
with open(target,'r') as f: #Reading JSON file
data = json.load(f)
specsA=('PreviousDraws',['DrawNumber'])
draw=(glom(data,specsA)) #list type; glom is a package to access nested data in JSON file.
print(draw)
# insert the draw to the dataframe
df['DrawNumbers'] = draw
for j in range(0,5):
specsB=('PreviousDraws',['WinningNumbers'],[f'{j}'],['Number'])
number=(glom(data,specsB)) #list type; glom is a package to access nested data in JSON file.
print(number)
# insert each number to the dataframe
df[f'Index{j}'] = number

Assuming that number is a nested list:
number = list(map(list, zip(*number))) # this transposes the nested list so that each list within the list now corresponds to one row of the desired df
pd.DataFrame(data=number, index=draw)
This will output the df in the desired format. Of course you can go ahead and label the columns as you like, etc.

numbers string of list separated with space in Python

I have a txt file that read line by line and the text file has some data as below. I am trying to extract the numbers so that I can process them as in array of something like that. The space in between dates and the start of the numbers are 'tabs" and the numbers have normal spaces.
04/10/2000 02 75 30 54 86
04/16/2000 63 63 48 32 12
04/15/2000 36 47 68 09 40
04/14/2000 06 27 31 36 43
04/13/2000 03 08 41 60 87
Here is the code I wrote:
for line in handle:
line = line.rstrip()
numberlist.append(line.split('\t'))
numbers=list()
numberlist=list()
for x in numberlist:
numbers.append(x[1])
print(numbers[:2]) # just to see sample output
Could someone help me to figure out? I checked some python tutorial even but the more I think about the issue, the more tricky and detailed it seems to me. (please note that this is not a homework)
Thanks

You can split on a tab \t to get 2 parts. Then split the second part on a space to get all the numbers.
strings = [
"04/10/2000 02 75 30 54 86",
"04/16/2000 63 63 48 32 12",
"04/15/2000 36 47 68 09 40",
"04/14/2000 06 27 31 36 43",
"04/13/2000 03 08 41 60 87"
]
numbers = list()
numberlist = list()
for s in strings:
lst = s.rstrip().split("\t")
if len(lst) > 1:
lst = lst[1].split(" ")
numberlist.append(lst)
for n in lst:
numbers.append(n)
print(numbers)
print(numberlist)
Output
['02', '75', '30', '54', '86', '63', '63', '48', '32', '12', '36', '47', '68', '09', '40', '06', '27', '31', '36', '43', '03', '08', '41', '60', '87']
[['02', '75', '30', '54', '86'], ['63', '63', '48', '32', '12'], ['36', '47', '68', '09', '40'], ['06', '27', '31', '36', '43'], ['03', '08', '41', '60', '87']]
Python demo

Merge two Pandas Dataframes

I have the following merging problem:
I have a time series of industry related data: weekly Profit Margins for 60 different industries over multiple years, which looks like this:
industry = pd.DataFrame({'Ind0': ['01', '02', '03', '04'],
'Ind1': ['11', '12', '13', '14'],
'Ind2': ['21', '22', '23', '24'],
'Ind3': ['31', '32', '33', '34']})
My 2nd dataframe consists of a few 1,000 stocks and their respective industries (each stock belongs to exactly one industry)
stocks = pd.DataFrame({'Stock0': ['Ind0'],
'Stock1': ['Ind1'],
'Stock2': ['Ind2'],
'Stock3': ['Ind3'],
'Stock4': ['Ind0'],
'Stock5': ['Ind1']})
I would like to create a new dataframe that contains the industry time series for each stock coming from the correct industry that the stock belongs to, i.e. something like this:
result = pd.DataFrame({'Stock0': ['01', '02', '03', '04'],
'Stock1': ['11', '12', '13', '14'],
'Stock2': ['21', '22', '23', '24'],
'Stock3': ['31', '32', '33', '34'],
'Stock4': ['01', '02', '03', '04'],
'Stock5': ['11', '12', '13', '14']})
I have tried a number of merge/concatenate approaches without success. Any help is appreciated.

Is this what you want?
stocks.T.merge(industry.T,left_on=0,right_index=True).drop(['key_0','0_x'],axis=1).rename(columns={'0_y':0}).T
Out[189]:
Stock0 Stock4 Stock1 Stock5 Stock2 Stock3
0 01 01 11 11 21 31
1 02 02 12 12 22 32
2 03 03 13 13 23 33
3 04 04 14 14 24 34

Pandas - Resort Column Location

I have a pandas frame. When I print the columns (shown below), its turns out that my columns are out of order. Is there a way to sort only the first 30 columns so they are in order (30,60,90...900)?
[in] df.columns
[out] Index(['120', '150', '180', '210', '240', '270', '30', '300', '330', '360',
'390', '420', '450', '480', '510', '540', '570', '60', '600', '630',
'660', '690', '720', '750', '780', '810', '840', '870', '90', '900',
'Item', 'Price', 'Size', 'Time', 'Type', 'Unnamed: 0'],
dtype='object')
The fixed frame would be as follows:
[out] Index(['30','60','90,'120', '150', '180', '210', '240', '270','300', '330', '360',
'390', '420', '450', '480', '510', '540', '570','600', '630',
'660', '690', '720', '750', '780', '810', '840', '870','900',
'Item', 'Price', 'Size', 'Time', 'Type', 'Unnamed: 0'],
dtype='object')

If you know that the columns will be named 30 through 900 in multiples of 30, you can generate that explicitly like this:
c = [str(i) for i in range(30, 901, 30)]
Then add it to the other columns:
c = c + ['Item', 'Price', 'Size', 'Time', 'Type', 'Unnamed: 0']
Then you should be able to access it as df[c]

You need select first column names, convert to int and sort. Then convert back to str if necessary and use reindex_axis:
np.sort(df.columns[:30].astype(int)).astype(str).tolist() +
df.columns[30:].tolist()
Sample:
df = pd.DataFrame(np.arange(36).reshape(1,-1),
columns=['120', '150', '180', '210', '240', '270', '30', '300',
'330', '360','390', '420', '450', '480', '510', '540', '570', '60', '600', '630',
'660', '690', '720', '750', '780', '810', '840', '870', '90', '900',
'Item', 'Price', 'Size', 'Time', 'Type', 'Unnamed: 0'])
print (df)
120 150 180 210 240 270 30 300 330 360 ... 840 870 90 \
0 0 1 2 3 4 5 6 7 8 9 ... 26 27 28
900 Item Price Size Time Type Unnamed: 0
0 29 30 31 32 33 34 35
[1 rows x 36 columns]
df = df.reindex_axis(np.sort(df.columns[:30].astype(int)).astype(str).tolist() +
df.columns[30:].tolist(), axis=1)
print (df)
30 60 90 120 150 180 210 240 270 300 ... 810 840 870 \
0 6 17 28 0 1 2 3 4 5 7 ... 25 26 27
900 Item Price Size Time Type Unnamed: 0
0 29 30 31 32 33 34 35
[1 rows x 36 columns]