Read more formats#

Read Google sheets#


import pandas as pd
sheet_id = '18tEk0FJTXEqZsa709DMmQzluUXJ6eoI2JmsZuqd1soE'
sheet_name = 'Sheet1'
url = f'https://docs.google.com/spreadsheets/d/{sheet_id}/gviz/tq?tqx=out:csv&sheet={sheet_name}'
df = pd.read_csv(url)
df.head()

Read jsonl#

import json
def read_jsonl(file):
    list_of_dics = []
    with open(file, 'r') as f:
        json_list = list(f)
        for string in json_list:
            list_of_dics += [json.loads(string)]
    return list_of_dics

Read Pickle#

import pickle5 as pickle

posts = pickle.load(open("./jsonl/filtered_post.pickle", "rb"))
with open("./jsonl/filtered_comment.pickle", "rb") as fin:
    comments = pickle.load(fin)

print("N of posts:", len(posts))
print("N of comments:", len(comments))

Read R RDA#

import pyreadr
raw = pyreadr.read_r("Boy-Girl_20210627.rda")
raw['allp.df']

Read feather#