I am trying to make a function that takes a threshold and determines which names from a csv file of song names and their lyrics that contain human names and the function
should create a csv file named outputfile that contains the number of distinct names, the name of
the song and the artist.
import csv
def findName(thresh, outputFile):
dictNames={}
with open('allNames.csv') as csvfile:
reader = csv.DictReader(csvfile, delimiter="\t")
for row in reader:
if row["name"] in dictNames:
dictNames[row["name"]] +=1
else:
dictNames[row["name"]]=1
with open(outputFile, "w", newline='') as outfile:
headers= ["song", "artist", "year"]
writer=csv.DictWriter(outfile, fieldnames=headers)
writer.writeheader()
for key, val in dictNames.items():
if val>= thresh:
writer.writerow({key: val})
csvfile.close()
outfile.close()
What's the rationale for not using Pandas here?
Not sure I fully understand your question, but I'm thinking something like:
df = pd.read_csv('allNames.csv')
#partition df after threshold
df['index'] = df.index
def partition_return(threshold, df):
df = df.loc[df['index'] >= threshold].reset_index(drop=true)
df = df[['song', 'artist', 'year]]
df['count_names_dist'] = len(df['artist'].unique())
df.to_csv('outfile.csv', index=False)
I have a CSV file with headers on row 0. The headers are often unique but sometimes they are not, for "comments" in this example. For each of several comments, the header is "Comment".
The problem with my function that makes dicts from CSVs is that it only returns the last column of Comment.
def csv_to_list_with_dicts(csvfile):
with open(csvfile) as f:
list_of_issues = [{k: v for k, v in row.items()}
for row in csv.DictReader(f, skipinitialspace=True)]
return list_of_issues
My CSV file columns are like this:
User;ID;Comment;Comment;Comment
If one of the headers is repeating, I need to add an index to make it unique (like Comment1;Comment2 without changing the CSV) in the dict or all comments included under just Comment.
This did return just the way I wanted. Just tweaked yours a small bit Happy Ahmad! HUGE THANKS!!! <3
def csv_to_list_with_dicts(csvfile):
with open(csvfile, "r") as file:
keys = file.readline().split(",")
alteredKeys = []
for eachKey in keys:
counter = 0
while(eachKey in alteredKeys):
counter += 1
eachKey = eachKey[:len(eachKey)-(0 if counter == 1 else 1)] + str(counter)
alteredKeys.append(eachKey)
list_of_issues = []
reader = csv.reader(file, delimiter=',', skipinitialspace=True)
for eachLine in reader:
eachIssue = dict()
columnIndex = 0
for eachColumn in eachLine:
if columnIndex < len(alteredKeys):
eachIssue[alteredKeys[columnIndex]] = eachColumn
columnIndex += 1
list_of_issues.append(eachIssue)
return list_of_issues
In this solution, I use an alterKey list that changes any repeated key in the header by adding an index at its end. Then, I iterate on the other lines of the CSV file and make a dictionary from each one.
def csv_to_list_with_dicts(csvfile):
with open(csvfile, "r") as file:
keys = file.readline().split(";")
alteredKeys = []
for eachKey in keys:
counter = 0
while(eachKey in alteredKeys):
counter += 1
eachKey = eachKey[:len(eachKey)-(0 if counter == 1 else 1)] + str(counter)
alteredKeys.append(eachKey)
list_of_issues = []
for eachLine in file:
eachIssue = dict()
columnIndex = 0
for eachColumn in eachLine.split(";")
if columnIndex < len(alteredKeys):
eachIssue[alteredKeys[columnIndex]] = eachColumn
columnIndex += 1
list_of_issues.append(eachIssue)
return list_of_issues
It woujld be fairly easy to write code that will automatically generate unique keys for you by simply keeping track of those already seen and generating a unique name for any encountered that conflicted with one before it. Checking for that would be quick if those seen were kept in a set which features fast membership testing.
For example, assume this was in a CSV file named non-unique.csv:
User;ID;Comment;Comment;Comment
Jose;1138;something1;something2;something3
Gene;2907;abc;def;ghi
Guido;6450;jkl;mno;pqr
Code:
import csv
def csv_to_list_with_dicts(csv_filename):
# Read the first row of the csv file.
with open(csv_filename, encoding='utf-8', newline='') as csv_file:
reader = csv.reader(csv_file, delimiter=';', skipinitialspace=True)
names = next(reader) # Header row.
# Create list of unique fieldnames for the namee in the header row.
seen = set()
fieldnames = []
for i, name in enumerate(names):
if name in seen:
name = f'_{i}'
else:
seen.add(name)
fieldnames.append(name)
# Read entire file and make each row a dictionary with keys based on the fieldnames.
with open(csv_filename, encoding='utf-8', newline='') as csv_file:
reader = csv.DictReader(csv_file, fieldnames=fieldnames, delimiter=';',
skipinitialspace=True)
next(reader) # Ignore header row.
return list(reader)
results = csv_to_list_with_dicts('non-unique.csv')
from pprint import pprint
pprint(results, sort_dicts=False, width=120)
Results:
[{'User': 'Jose', 'ID': '1138', 'Comment': 'something1', '_3': 'something2', '_4': 'something3'},
{'User': 'Gene', 'ID': '2907', 'Comment': 'abc', '_3': 'def', '_4': 'ghi'},
{'User': 'Guido', 'ID': '6450', 'Comment': 'jkl', '_3': 'mno', '_4': 'pqr'}]
I am trying to store some data in csv file. I am able to store data but it looks like this
1901,1909,1911,1913,1917
5,5,5,4,6
the first row is year names and second row is values.
my code is as follow
import os
import csv
from collections import Counter
from csv import reader
def read_data(filename):
year = 3
with open(filename) as f:
next(f, None) # discard header
year2rel = Counter(int(line[YEAR]) for line in reader(f))
return year2rel
file_exists = os.path.isfile('mycsvfile.csv')
def store_data(value):
my_dict = read_data(filename)
print 'my_dict: ', my_dict
with open('mycsvfile.csv', 'wb') as f:
w = csv.DictWriter(f, my_dict.keys())
if not file_exists:
w.writeheader()
print 'w: ', w
w.writerow(my_dict)
if __name__ == '__main__':
filename = '/home/rob/songs_detail.csv'
a = read_songs(filename)
b = store_data(a)
but I want to include headers so that it looks like
year values
1901 5
1909 5
1911 5
1913 4
1917 6
I tried to change my code but it doesn't work for me well. I tried something like below but unsuccessful. thanks for any tip or help.
def store_data(value):
file_exists = os.path.isfile('mycsvfile.csv')
my_dict = read_data(filename)
print 'my_dict: ', my_dict
with open('mycsvfile.csv', 'wb') as csvfile:
headers = ['year', 'values']
writer = csv.DictWriter(csvfile, delimiter=',', lineterminator='\n',fieldnames=headers)
if not file_exists:
writer.writeheader() # file doesn't exist yet, write a header
writer.writerow({'year': my_dict[0], 'values': my_dict[1]})
this give me the following error.
'ValueError: dict contains fields not in fieldnames: 'values', 'year'
'
I solve my question and the code is as follow, might be helpful for someone.
def store_data(value):
file_exists = os.path.isfile('mycsvfile.csv')
my_dict = read_data(filename)
print 'my_dict: ', my_dict
print 'type of: ', type(my_dict)
with open('mycsvfile.csv', 'wb') as csvfile:
headers = ['year', 'values']
writer = csv.DictWriter(csvfile, delimiter=',', lineterminator='\n',fieldnames=headers)
if not file_exists:
writer.writeheader()
for k, v in my_dict.items():
print(k, v)
writer.writerow({'year': k, 'values': v})
Actually I was missing to add loop in the proper way, so it results always in the csv file without headers. now it works perfectly fine according to my requirements.
I want to sort the data in a csv file alphabetically according to the contents in the first column. For example, if the file contained:
city/month,Jan,Feb,Mar,Apr
Melbourne,41.2,35.5,37.4,29.3
Brisbane,31.3,40.2,37.9,29
Darwin,34,34,33.2,34.5
it would be sorted as:
city/month,Jan,Feb,Mar,Apr
Brisbane,31.3,40.2,37.9,29
Darwin,34,34,33.2,34.5
Melbourne,41.2,35.5,37.4,29.3
what I've done so far, sorts correctly but it doesn't return the answer correctly, instead of returning it in the table format, it returns everything as a list - any idea why that is?
import csv
import operator
def sort_records(csv_filename, new_filename):
f = open(csv_filename)
csv1 = csv.reader(f, delimiter = ',')
new_filename = sorted(csv1)
return new_filename
f.close()
>>> import csv
>>> import operator
>>> def sort_records(csv_filename, new_filename):
... with open(csv_filename, 'r') as i, open(new_filename, 'w') as o:
... reader = csv.reader(i, delimiter = ',')
... writer = csv.writer(o, delimiter=',')
... writer.writerow(next(reader)) # header row
... writer.writerows(sorted(reader, key=operator.itemgetter(0)))
>>> sort_records('a.csv', 'b.csv')
Here's my code, really simple stuff...
import csv
import json
csvfile = open('file.csv', 'r')
jsonfile = open('file.json', 'w')
fieldnames = ("FirstName","LastName","IDNumber","Message")
reader = csv.DictReader( csvfile, fieldnames)
out = json.dumps( [ row for row in reader ] )
jsonfile.write(out)
Declare some field names, the reader uses CSV to read the file, and the filed names to dump the file to a JSON format. Here's the problem...
Each record in the CSV file is on a different row. I want the JSON output to be the same way. The problem is it dumps it all on one giant, long line.
I've tried using something like for line in csvfile: and then running my code below that with reader = csv.DictReader( line, fieldnames) which loops through each line, but it does the entire file on one line, then loops through the entire file on another line... continues until it runs out of lines.
Any suggestions for correcting this?
Edit: To clarify, currently I have: (every record on line 1)
[{"FirstName":"John","LastName":"Doe","IDNumber":"123","Message":"None"},{"FirstName":"George","LastName":"Washington","IDNumber":"001","Message":"Something"}]
What I'm looking for: (2 records on 2 lines)
{"FirstName":"John","LastName":"Doe","IDNumber":"123","Message":"None"}
{"FirstName":"George","LastName":"Washington","IDNumber":"001","Message":"Something"}
Not each individual field indented/on a separate line, but each record on it's own line.
Some sample input.
"John","Doe","001","Message1"
"George","Washington","002","Message2"
The problem with your desired output is that it is not valid json document,; it's a stream of json documents!
That's okay, if its what you need, but that means that for each document you want in your output, you'll have to call json.dumps.
Since the newline you want separating your documents is not contained in those documents, you're on the hook for supplying it yourself. So we just need to pull the loop out of the call to json.dump and interpose newlines for each document written.
import csv
import json
csvfile = open('file.csv', 'r')
jsonfile = open('file.json', 'w')
fieldnames = ("FirstName","LastName","IDNumber","Message")
reader = csv.DictReader( csvfile, fieldnames)
for row in reader:
json.dump(row, jsonfile)
jsonfile.write('\n')
You can use Pandas DataFrame to achieve this, with the following Example:
import pandas as pd
csv_file = pd.DataFrame(pd.read_csv("path/to/file.csv", sep = ",", header = 0, index_col = False))
csv_file.to_json("/path/to/new/file.json", orient = "records", date_format = "epoch", double_precision = 10, force_ascii = True, date_unit = "ms", default_handler = None)
import csv
import json
file = 'csv_file_name.csv'
json_file = 'output_file_name.json'
#Read CSV File
def read_CSV(file, json_file):
csv_rows = []
with open(file) as csvfile:
reader = csv.DictReader(csvfile)
field = reader.fieldnames
for row in reader:
csv_rows.extend([{field[i]:row[field[i]] for i in range(len(field))}])
convert_write_json(csv_rows, json_file)
#Convert csv data into json
def convert_write_json(data, json_file):
with open(json_file, "w") as f:
f.write(json.dumps(data, sort_keys=False, indent=4, separators=(',', ': '))) #for pretty
f.write(json.dumps(data))
read_CSV(file,json_file)
Documentation of json.dumps()
I took #SingleNegationElimination's response and simplified it into a three-liner that can be used in a pipeline:
import csv
import json
import sys
for row in csv.DictReader(sys.stdin):
json.dump(row, sys.stdout)
sys.stdout.write('\n')
You can try this
import csvmapper
# how does the object look
mapper = csvmapper.DictMapper([
[
{ 'name' : 'FirstName'},
{ 'name' : 'LastName' },
{ 'name' : 'IDNumber', 'type':'int' },
{ 'name' : 'Messages' }
]
])
# parser instance
parser = csvmapper.CSVParser('sample.csv', mapper)
# conversion service
converter = csvmapper.JSONConverter(parser)
print converter.doConvert(pretty=True)
Edit:
Simpler approach
import csvmapper
fields = ('FirstName', 'LastName', 'IDNumber', 'Messages')
parser = CSVParser('sample.csv', csvmapper.FieldMapper(fields))
converter = csvmapper.JSONConverter(parser)
print converter.doConvert(pretty=True)
I see this is old but I needed the code from SingleNegationElimination however I had issue with the data containing non utf-8 characters. These appeared in fields I was not overly concerned with so I chose to ignore them. However that took some effort. I am new to python so with some trial and error I got it to work. The code is a copy of SingleNegationElimination with the extra handling of utf-8. I tried to do it with https://docs.python.org/2.7/library/csv.html but in the end gave up. The below code worked.
import csv, json
csvfile = open('file.csv', 'r')
jsonfile = open('file.json', 'w')
fieldnames = ("Scope","Comment","OOS Code","In RMF","Code","Status","Name","Sub Code","CAT","LOB","Description","Owner","Manager","Platform Owner")
reader = csv.DictReader(csvfile , fieldnames)
code = ''
for row in reader:
try:
print('+' + row['Code'])
for key in row:
row[key] = row[key].decode('utf-8', 'ignore').encode('utf-8')
json.dump(row, jsonfile)
jsonfile.write('\n')
except:
print('-' + row['Code'])
raise
Add the indent parameter to json.dumps
data = {'this': ['has', 'some', 'things'],
'in': {'it': 'with', 'some': 'more'}}
print(json.dumps(data, indent=4))
Also note that, you can simply use json.dump with the open jsonfile:
json.dump(data, jsonfile)
Use pandas and the json library:
import pandas as pd
import json
filepath = "inputfile.csv"
output_path = "outputfile.json"
df = pd.read_csv(filepath)
# Create a multiline json
json_list = json.loads(df.to_json(orient = "records"))
with open(output_path, 'w') as f:
for item in json_list:
f.write("%s\n" % item)
How about using Pandas to read the csv file into a DataFrame (pd.read_csv), then manipulating the columns if you want (dropping them or updating values) and finally converting the DataFrame back to JSON (pd.DataFrame.to_json).
Note: I haven't checked how efficient this will be but this is definitely one of the easiest ways to manipulate and convert a large csv to json.
As slight improvement to #MONTYHS answer, iterating through a tup of fieldnames:
import csv
import json
csvfilename = 'filename.csv'
jsonfilename = csvfilename.split('.')[0] + '.json'
csvfile = open(csvfilename, 'r')
jsonfile = open(jsonfilename, 'w')
reader = csv.DictReader(csvfile)
fieldnames = ('FirstName', 'LastName', 'IDNumber', 'Message')
output = []
for each in reader:
row = {}
for field in fieldnames:
row[field] = each[field]
output.append(row)
json.dump(output, jsonfile, indent=2, sort_keys=True)
def read():
noOfElem = 200 # no of data you want to import
csv_file_name = "hashtag_donaldtrump.csv" # csv file name
json_file_name = "hashtag_donaldtrump.json" # json file name
with open(csv_file_name, mode='r') as csv_file:
csv_reader = csv.DictReader(csv_file)
with open(json_file_name, 'w') as json_file:
i = 0
json_file.write("[")
for row in csv_reader:
i = i + 1
if i == noOfElem:
json_file.write("]")
return
json_file.write(json.dumps(row))
if i != noOfElem - 1:
json_file.write(",")
Change the above three parameter, everything will be done.
import csv
import json
csvfile = csv.DictReader('filename.csv', 'r'))
output =[]
for each in csvfile:
row ={}
row['FirstName'] = each['FirstName']
row['LastName'] = each['LastName']
row['IDNumber'] = each ['IDNumber']
row['Message'] = each['Message']
output.append(row)
json.dump(output,open('filename.json','w'),indent=4,sort_keys=False)