Error when converting string and array data from CSV file to tfrecords

I am following these examples to convert my csv file to tfrecords.

This is the code I attempted

csv = pd.read_csv("ehealth.csv").values
with tf.python_io.TFRecordWriter("ehealth.tfrecords") as writer:
    for row in csv:
        question, answer, question_bert, answer_bert = row[0], row[1] , row[1], row[2]
        example = tf.train.Example()
        example.features.feature["question"].bytes_list.value.extend(question.encode("utf8"))
        example.features.feature["answer"].bytes_list.value.extend(answer.encode("utf8"))
        example.features.feature["question_bert"].float_list.value.extend(question_bert)
        example.features.feature["answer_bert"].float_list.value.append(answer_bert)
        writer.write(example.SerializeToString())

This is my error

TypeError                                 Traceback (most recent call last) <ipython-input-36-0a8c5e073d84> in <module>()
      4         question, answer, question_bert, answer_bert = row[0], row[1] , row[1], row[2]
      5         example = tf.train.Example()
----> 6         example.features.feature["question"].bytes_list.value.extend(question.encode("utf8"))
      7         example.features.feature["answer"].bytes_list.value.extend(answer.encode("utf8"))
      8         example.features.feature["question_bert"].float_list.value.extend(question_bert)

TypeError: 104 has type int, but expected one of: bytes

It looks like there is an issue when encoding the string. I commented those two lines to make sure everything else is working correctly,

csv = pd.read_csv("ehealth.csv").values
with tf.python_io.TFRecordWriter("ehealth.tfrecords") as writer:
    for row in csv:
        question, answer, question_bert, answer_bert = row[0], row[1] , row[1], row[2]
        example = tf.train.Example()
#         example.features.feature["question"].bytes_list.value.extend(question)
#         example.features.feature["answer"].bytes_list.value.extend(answer)
        example.features.feature["question_bert"].float_list.value.extend(question_bert)
        example.features.feature["answer_bert"].float_list.value.append(answer_bert)
        writer.write(example.SerializeToString())

but then I get these errors

TypeError                                 Traceback (most recent call last) <ipython-input-13-565b43316ef5> in <module>()
      6 #         example.features.feature["question"].bytes_list.value.extend(question)
      7 #         example.features.feature["answer"].bytes_list.value.extend(answer)
----> 8         example.features.feature["question_bert"].float_list.value.extend(question_bert)
      9         example.features.feature["answer_bert"].float_list.value.append(answer_bert)
     10         writer.write(example.SerializeToString())

TypeError: 's' has type str, but expected one of: int, long, float

It turns out that the issue is pandas is interpreting my array as a string instead of an array

type( csv[0][2])

->str

Furthermore, it looks like I have to use example.SerializeToString() since I have an array, but not sure how to go about doing that.

Below is the full code to reproduce the errors including code which downloads the csv file from a google drive.

import pandas as pd
import numpy as np
import requests
import tensorflow as tf

def download_file_from_google_drive(id, destination):
    URL = "https://docs.google.com/uc?export=download"

    session = requests.Session()

    response = session.get(URL, params = { 'id' : id }, stream = True)
    token = get_confirm_token(response)

    if token:
        params = { 'id' : id, 'confirm' : token }
        response = session.get(URL, params = params, stream = True)

    save_response_content(response, destination)    

def get_confirm_token(response):
    for key, value in response.cookies.items():
        if key.startswith('download_warning'):
            return value

    return None

def save_response_content(response, destination):
    CHUNK_SIZE = 32768

    with open(destination, "wb") as f:
        for chunk in response.iter_content(CHUNK_SIZE):
            if chunk: # filter out keep-alive new chunks
                f.write(chunk)

# download_file_from_google_drive('1rMjqKkMnt6_vROrGmlTGStNGmwPO4YFX', 'model.zip') #

file_id = '1anbEwfViu9Rzu7tWKgPb_We1EwbA4x1-'
destination = 'ehealth.csv'
download_file_from_google_drive(file_id, destination)

healthdata=pd.read_csv('ehealth.csv')
healthdata.head()

csv = pd.read_csv("ehealth.csv").values
with tf.python_io.TFRecordWriter("ehealth.tfrecords") as writer:
    for row in csv:
        question, answer, question_bert, answer_bert = row[0], row[1] , row[1], row[2]
        example = tf.train.Example()
        example.features.feature["question"].bytes_list.value.extend(question)
        example.features.feature["answer"].bytes_list.value.extend(answer)
        example.features.feature["question_bert"].float_list.value.extend(question_bert)
        example.features.feature["answer_bert"].float_list.value.append(answer_bert)
        writer.write(example.SerializeToString())


csv = pd.read_csv("ehealth.csv").values
with tf.python_io.TFRecordWriter("ehealth.tfrecords") as writer:
    for row in csv:
        question, answer, question_bert, answer_bert = row[0], row[1] , row[1], row[2]
        example = tf.train.Example()
#         example.features.feature["question"].bytes_list.value.extend(question)
#         example.features.feature["answer"].bytes_list.value.extend(answer)
        example.features.feature["question_bert"].float_list.value.extend(question_bert)
        example.features.feature["answer_bert"].float_list.value.append(answer_bert)
        writer.write(example.SerializeToString())