Python

python survey data anaylsis - html to tistory

summerorange 2022. 6. 11. 10:11

In [ ]:

from google.colab import drive
drive.mount('/content/drive')

Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount("/content/drive", force_remount=True).

In [ ]:

%cd /content/drive/MyDrive/Study

/content/drive/MyDrive/Study

Bring Data¶

In [ ]:

import pandas as pd
import os

In [ ]:

dataset = pd.read_excel("Data.xlsx", sheet_name="Edited_Data")
dataset.head()

Out[ ]:

	Respondent ID	Start Date	End Date	Email Address	First Name	Last Name	Custom Data 1	Identify which division you work in.-Response	Identify which division you work in.-Other (please specify)	Which of the following best describes your position level?-Response	...	Question 29-Response 8	Question 29-Response 9	Question 29-Response 10	Question 29-Response 11	Question 29-Response 12	Question 29-Response 13	Question 29-Response 14	Question 30-Response 1	Question 30-Response 2	Question 30-Response 3
0	5379192392	2021-01-22 12:01:17	2021-01-22 12:40:34	NaN	NaN	NaN	NaN	Infrastructure	NaN	Staff	...	NaN	Answer 8	Answer 8	Answer 4	NaN	NaN	Answer 5	NaN	NaN	NaN
1	2658722536	2021-01-22 06:56:37	2021-01-22 07:34:10	NaN	NaN	NaN	NaN	Finance	NaN	Staff	...	NaN	Answer 5	NaN	NaN	Answer 2	NaN	Answer 5	NaN	NaN	Answer 1
2	4044163394	2021-01-22 06:35:18	2021-01-22 06:47:32	NaN	NaN	NaN	NaN	Infrastructure	NaN	Department Lead	...	NaN	NaN	Answer 4	Answer 4	Answer 6	NaN	Answer 6	NaN	Answer 1	NaN
3	5535865599	2021-01-21 21:29:32	2021-01-21 21:40:24	NaN	NaN	NaN	NaN	Infrastructure	NaN	Manager	...	Answer 2	Answer 5	Answer 7	NaN	Answer 6	NaN	Answer 7	Answer 7	Answer 1	Answer 6
4	3356802928	2021-01-21 17:26:39	2021-01-21 17:44:40	NaN	NaN	NaN	NaN	Port Operations	NaN	Manager	...	NaN	Answer 5	Answer 4	Answer 4	Answer 7	Answer 7	NaN	Answer 7	NaN	Answer 8

5 rows × 100 columns

Data copy¶

In [ ]:

from google.colab.output import eval_js
eval_js('google.colab.output.setIframeHeight("500")')

In [ ]:

# colab에서 표줄이는데 사용하는 코드?
from IPython.display import Javascript
display(Javascript('''google.colab.output.setIframeHeight(0, true, {maxHeight: 500})'''))

In [ ]:

from IPython.display import Javascript
display(Javascript('''google.colab.output.setIframeHeight(0, true, {maxHeight: 500})'''))
# 사본으로 작업
dataset_modified=dataset.copy()
dataset_modified.head()

Out[ ]:

	Respondent ID	Start Date	End Date	Email Address	First Name	Last Name	Custom Data 1	Identify which division you work in.-Response	Identify which division you work in.-Other (please specify)	Which of the following best describes your position level?-Response	...	Question 29-Response 8	Question 29-Response 9	Question 29-Response 10	Question 29-Response 11	Question 29-Response 12	Question 29-Response 13	Question 29-Response 14	Question 30-Response 1	Question 30-Response 2	Question 30-Response 3
0	5379192392	2021-01-22 12:01:17	2021-01-22 12:40:34	NaN	NaN	NaN	NaN	Infrastructure	NaN	Staff	...	NaN	Answer 8	Answer 8	Answer 4	NaN	NaN	Answer 5	NaN	NaN	NaN
1	2658722536	2021-01-22 06:56:37	2021-01-22 07:34:10	NaN	NaN	NaN	NaN	Finance	NaN	Staff	...	NaN	Answer 5	NaN	NaN	Answer 2	NaN	Answer 5	NaN	NaN	Answer 1
2	4044163394	2021-01-22 06:35:18	2021-01-22 06:47:32	NaN	NaN	NaN	NaN	Infrastructure	NaN	Department Lead	...	NaN	NaN	Answer 4	Answer 4	Answer 6	NaN	Answer 6	NaN	Answer 1	NaN
3	5535865599	2021-01-21 21:29:32	2021-01-21 21:40:24	NaN	NaN	NaN	NaN	Infrastructure	NaN	Manager	...	Answer 2	Answer 5	Answer 7	NaN	Answer 6	NaN	Answer 7	Answer 7	Answer 1	Answer 6
4	3356802928	2021-01-21 17:26:39	2021-01-21 17:44:40	NaN	NaN	NaN	NaN	Port Operations	NaN	Manager	...	NaN	Answer 5	Answer 4	Answer 4	Answer 7	Answer 7	NaN	Answer 7	NaN	Answer 8

5 rows × 100 columns

In [ ]:

dataset.columns
columns_to_drop = ['Start Date', 'End Date', 'Email Address', 'First Name', 'Last Name', 'Custom Data 1']

In [ ]:

dataset_modified = dataset_modified.drop(columns=columns_to_drop)

In [ ]:

from IPython.display import Javascript
display(Javascript('''google.colab.output.setIframeHeight(0, true, {maxHeight: 500})'''))
dataset_modified.head()

Out[ ]:

	Respondent ID	Identify which division you work in.-Response	Identify which division you work in.-Other (please specify)	Which of the following best describes your position level?-Response	Which generation are you apart of?-Response	Please select the gender in which you identify.-Response	Which duration range best aligns with your tenure at your company?-Response	Which of the following best describes your employment type?-Response	Question 1-Response	Question 2-Response	...	Question 29-Response 8	Question 29-Response 9	Question 29-Response 10	Question 29-Response 11	Question 29-Response 12	Question 29-Response 13	Question 29-Response 14	Question 30-Response 1	Question 30-Response 2	Question 30-Response 3
0	5379192392	Infrastructure	NaN	Staff	Generation X (born between 1965-1980)	Male	0-2 years	Full time Employee	NaN	Answer 6	...	NaN	Answer 8	Answer 8	Answer 4	NaN	NaN	Answer 5	NaN	NaN	NaN
1	2658722536	Finance	NaN	Staff	NaN	NaN	10+ years	Full time Employee	Answer 4	Answer 2	...	NaN	Answer 5	NaN	NaN	Answer 2	NaN	Answer 5	NaN	NaN	Answer 1
2	4044163394	Infrastructure	NaN	Department Lead	Generation X (born between 1965-1980)	Male	3-5 years	Full time Employee	Answer 5	Answer 7	...	NaN	NaN	Answer 4	Answer 4	Answer 6	NaN	Answer 6	NaN	Answer 1	NaN
3	5535865599	Infrastructure	NaN	Manager	Millennial (born between 1981-2000)	Non-Binary	5-10 years	Full time Employee	Answer 1	Answer 1	...	Answer 2	Answer 5	Answer 7	NaN	Answer 6	NaN	Answer 7	Answer 7	Answer 1	Answer 6
4	3356802928	Port Operations	NaN	Manager	Generation X (born between 1965-1980)	Female	10+ years	Full time Employee	NaN	Answer 3	...	NaN	Answer 5	Answer 4	Answer 4	Answer 7	Answer 7	NaN	Answer 7	NaN	Answer 8

5 rows × 94 columns

In [ ]:

id_vars = list(dataset_modified.columns)[:8]
value_vars = list(dataset_modified.columns) [8:]
# value_vars

In [ ]:

from IPython.display import Javascript
display(Javascript('''google.colab.output.setIframeHeight(0, true, {maxHeight: 500})'''))

dataset_melted = dataset_modified.melt(id_vars=id_vars, value_vars=value_vars, var_name="Question + Subquestion", value_name="Answer")
dataset_melted

Out[ ]:

	Respondent ID	Identify which division you work in.-Response	Identify which division you work in.-Other (please specify)	Which of the following best describes your position level?-Response	Which generation are you apart of?-Response	Please select the gender in which you identify.-Response	Which duration range best aligns with your tenure at your company?-Response	Which of the following best describes your employment type?-Response	Question + Subquestion	Answer
0	5379192392	Infrastructure	NaN	Staff	Generation X (born between 1965-1980)	Male	0-2 years	Full time Employee	Question 1-Response	NaN
1	2658722536	Finance	NaN	Staff	NaN	NaN	10+ years	Full time Employee	Question 1-Response	Answer 4
2	4044163394	Infrastructure	NaN	Department Lead	Generation X (born between 1965-1980)	Male	3-5 years	Full time Employee	Question 1-Response	Answer 5
3	5535865599	Infrastructure	NaN	Manager	Millennial (born between 1981-2000)	Non-Binary	5-10 years	Full time Employee	Question 1-Response	Answer 1
4	3356802928	Port Operations	NaN	Manager	Generation X (born between 1965-1980)	Female	10+ years	Full time Employee	Question 1-Response	NaN
...	...	...	...	...	...	...	...	...	...	...
17023	7940065082	Infrastructure	NaN	Department Lead	Baby Boomer (born between 1946-1964)	Male	10+ years	Full time Employee	Question 30-Response 3	Answer 8
17024	5157705612	Finance	NaN	Staff	Millennial (born between 1981-2000)	Female	5-10 years	Full time Employee	Question 30-Response 3	Answer 6
17025	9920755555	Port Operations	NaN	Staff	Millennial (born between 1981-2000)	Female	3-5 years	Full time Employee	Question 30-Response 3	NaN
17026	6638341389	Infrastructure	NaN	Manager	Millennial (born between 1981-2000)	Female	3-5 years	Full time Employee	Question 30-Response 3	NaN
17027	8114622230	Information Technology	NaN	Staff	Prefer not to answer	Male	5-10 years	Full time Employee	Question 30-Response 3	NaN

17028 rows × 10 columns

In [ ]:

questions_import = pd.read_excel("/content/drive/MyDrive/Study/Data.xlsx", sheet_name="Question")
questions_import

Out[ ]:

	Raw Question	Raw Subquestion	Question	Subquestion	Question + Subquestion
0	Respondent ID	NaN	Respondent ID	NaN	Respondent ID
1	Start Date	NaN	Start Date	NaN	Start Date
2	End Date	NaN	End Date	NaN	End Date
3	Email Address	NaN	Email Address	NaN	Email Address
4	First Name	NaN	First Name	NaN	First Name
...	...	...	...	...	...
95	NaN	Response 13	Question 29	Response 13	Question 29-Response 13
96	NaN	Response 14	Question 29	Response 14	Question 29-Response 14
97	Question 30	Response 1	Question 30	Response 1	Question 30-Response 1
98	NaN	Response 2	Question 30	Response 2	Question 30-Response 2
99	NaN	Response 3	Question 30	Response 3	Question 30-Response 3

100 rows × 5 columns

In [ ]:

questions = questions_import.copy()
questions.columns

Out[ ]:

Index(['Raw Question', 'Raw Subquestion', 'Question', 'Subquestion',
       'Question + Subquestion'],
      dtype='object')

In [ ]:

questions.drop(columns=['Raw Question', 'Raw Subquestion', 'Subquestion'], inplace=True)

In [ ]:

questions

Out[ ]:

	Question	Question + Subquestion
0	Respondent ID	Respondent ID
1	Start Date	Start Date
2	End Date	End Date
3	Email Address	Email Address
4	First Name	First Name
...	...	...
95	Question 29	Question 29-Response 13
96	Question 29	Question 29-Response 14
97	Question 30	Question 30-Response 1
98	Question 30	Question 30-Response 2
99	Question 30	Question 30-Response 3

100 rows × 2 columns

In [ ]:

#questions.dropna(inplace=True)
questions

Out[ ]:

	Question	Question + Subquestion
0	Respondent ID	Respondent ID
1	Start Date	Start Date
2	End Date	End Date
3	Email Address	Email Address
4	First Name	First Name
...	...	...
95	Question 29	Question 29-Response 13
96	Question 29	Question 29-Response 14
97	Question 30	Question 30-Response 1
98	Question 30	Question 30-Response 2
99	Question 30	Question 30-Response 3

100 rows × 2 columns

In [ ]:

dataset_merged = pd.merge(left=dataset_melted, right=questions, how="left", left_on="Question + Subquestion", right_on="Question + Subquestion")
print("Original Data", len(dataset_melted))
print("Merged Data", len(dataset_merged))

Original Data 17028
Merged Data 17028

In [ ]:

dataset_merged.head()

Out[ ]:

	Respondent ID	Identify which division you work in.-Response	Identify which division you work in.-Other (please specify)	Which of the following best describes your position level?-Response	Which generation are you apart of?-Response	Please select the gender in which you identify.-Response	Which duration range best aligns with your tenure at your company?-Response	Which of the following best describes your employment type?-Response	Question + Subquestion	Answer	Question
0	5379192392	Infrastructure	NaN	Staff	Generation X (born between 1965-1980)	Male	0-2 years	Full time Employee	Question 1-Response	NaN	Question 1
1	2658722536	Finance	NaN	Staff	NaN	NaN	10+ years	Full time Employee	Question 1-Response	Answer 4	Question 1
2	4044163394	Infrastructure	NaN	Department Lead	Generation X (born between 1965-1980)	Male	3-5 years	Full time Employee	Question 1-Response	Answer 5	Question 1
3	5535865599	Infrastructure	NaN	Manager	Millennial (born between 1981-2000)	Non-Binary	5-10 years	Full time Employee	Question 1-Response	Answer 1	Question 1
4	3356802928	Port Operations	NaN	Manager	Generation X (born between 1965-1980)	Female	10+ years	Full time Employee	Question 1-Response	NaN	Question 1

In [ ]:

dataset_merged.groupby("Question")["Answer"].nunique()

Out[ ]:

Question
Question 1     8
Question 10    8
Question 11    8
Question 12    8
Question 13    8
Question 14    8
Question 15    8
Question 16    8
Question 17    8
Question 18    8
Question 19    8
Question 2     8
Question 20    8
Question 21    8
Question 22    8
Question 23    8
Question 24    8
Question 25    8
Question 26    8
Question 27    8
Question 28    8
Question 29    8
Question 3     8
Question 30    8
Question 4     8
Question 5     8
Question 6     8
Question 7     8
Question 8     8
Question 9     8
Name: Answer, dtype: int64

In [ ]:

dataset_merged[dataset_merged["Answer"].notna()]

Out[ ]:

	Respondent ID	Identify which division you work in.-Response	Identify which division you work in.-Other (please specify)	Which of the following best describes your position level?-Response	Which generation are you apart of?-Response	Please select the gender in which you identify.-Response	Which duration range best aligns with your tenure at your company?-Response	Which of the following best describes your employment type?-Response	Question + Subquestion	Answer	Question
1	2658722536	Finance	NaN	Staff	NaN	NaN	10+ years	Full time Employee	Question 1-Response	Answer 4	Question 1
2	4044163394	Infrastructure	NaN	Department Lead	Generation X (born between 1965-1980)	Male	3-5 years	Full time Employee	Question 1-Response	Answer 5	Question 1
3	5535865599	Infrastructure	NaN	Manager	Millennial (born between 1981-2000)	Non-Binary	5-10 years	Full time Employee	Question 1-Response	Answer 1	Question 1
5	3399511781	Infrastructure	NaN	Staff	Generation X (born between 1965-1980)	Male	3-5 years	Full time Employee	Question 1-Response	Answer 8	Question 1
6	9860597462	Infrastructure	NaN	Department Lead	Baby Boomer (born between 1946-1964)	Male	10+ years	Full time Employee	Question 1-Response	Answer 8	Question 1
...	...	...	...	...	...	...	...	...	...	...	...
17017	9735550076	People	NaN	Staff	Generation X (born between 1965-1980)	Male	5-10 years	Full time Employee	Question 30-Response 3	Answer 5	Question 30
17020	7325851635	Infrastructure	NaN	Manager	Millennial (born between 1981-2000)	Prefer not to answer	3-5 years	Full time Employee	Question 30-Response 3	Answer 5	Question 30
17021	3370365802	Port Security & Emergency Operations	NaN	Staff	Generation X (born between 1965-1980)	Female	0-2 years	Full time Employee	Question 30-Response 3	Answer 6	Question 30
17023	7940065082	Infrastructure	NaN	Department Lead	Baby Boomer (born between 1946-1964)	Male	10+ years	Full time Employee	Question 30-Response 3	Answer 8	Question 30
17024	5157705612	Finance	NaN	Staff	Millennial (born between 1981-2000)	Female	5-10 years	Full time Employee	Question 30-Response 3	Answer 6	Question 30

9664 rows × 11 columns

In [ ]:

respondents = dataset_merged[dataset_merged["Answer"].notna()]
respondents = respondents.groupby("Question")["Respondent ID"].nunique().reset_index()
respondents.rename(columns={"Respondent ID":"Respondents"}, inplace=True)
respondents

Out[ ]:

	Question	Respondents
0	Question 1	119
1	Question 10	198
2	Question 11	164
3	Question 12	114
4	Question 13	108
5	Question 14	105
6	Question 15	114
7	Question 16	117
8	Question 17	135
9	Question 18	109
10	Question 19	157
11	Question 2	118
12	Question 20	105
13	Question 21	127
14	Question 22	160
15	Question 23	120
16	Question 24	195
17	Question 25	198
18	Question 26	193
19	Question 27	153
20	Question 28	119
21	Question 29	198
22	Question 3	117
23	Question 30	182
24	Question 4	161
25	Question 5	194
26	Question 6	196
27	Question 7	162
28	Question 8	190
29	Question 9	188

In [ ]:

dataset_merged_two = pd.merge(left=dataset_merged, right=respondents, how="left", left_on="Question", right_on="Question")
print("Original Data", len(dataset_merged))
print("Merged Data", len(dataset_merged_two))
dataset_merged_two

Original Data 17028
Merged Data 17028

Out[ ]:

	Respondent ID	Identify which division you work in.-Response	Identify which division you work in.-Other (please specify)	Which of the following best describes your position level?-Response	Which generation are you apart of?-Response	Please select the gender in which you identify.-Response	Which duration range best aligns with your tenure at your company?-Response	Which of the following best describes your employment type?-Response	Question + Subquestion	Answer	Question	Respondents
0	5379192392	Infrastructure	NaN	Staff	Generation X (born between 1965-1980)	Male	0-2 years	Full time Employee	Question 1-Response	NaN	Question 1	119
1	2658722536	Finance	NaN	Staff	NaN	NaN	10+ years	Full time Employee	Question 1-Response	Answer 4	Question 1	119
2	4044163394	Infrastructure	NaN	Department Lead	Generation X (born between 1965-1980)	Male	3-5 years	Full time Employee	Question 1-Response	Answer 5	Question 1	119
3	5535865599	Infrastructure	NaN	Manager	Millennial (born between 1981-2000)	Non-Binary	5-10 years	Full time Employee	Question 1-Response	Answer 1	Question 1	119
4	3356802928	Port Operations	NaN	Manager	Generation X (born between 1965-1980)	Female	10+ years	Full time Employee	Question 1-Response	NaN	Question 1	119
...	...	...	...	...	...	...	...	...	...	...	...	...
17023	7940065082	Infrastructure	NaN	Department Lead	Baby Boomer (born between 1946-1964)	Male	10+ years	Full time Employee	Question 30-Response 3	Answer 8	Question 30	182
17024	5157705612	Finance	NaN	Staff	Millennial (born between 1981-2000)	Female	5-10 years	Full time Employee	Question 30-Response 3	Answer 6	Question 30	182
17025	9920755555	Port Operations	NaN	Staff	Millennial (born between 1981-2000)	Female	3-5 years	Full time Employee	Question 30-Response 3	NaN	Question 30	182
17026	6638341389	Infrastructure	NaN	Manager	Millennial (born between 1981-2000)	Female	3-5 years	Full time Employee	Question 30-Response 3	NaN	Question 30	182
17027	8114622230	Information Technology	NaN	Staff	Prefer not to answer	Male	5-10 years	Full time Employee	Question 30-Response 3	NaN	Question 30	182

17028 rows × 12 columns

In [ ]:

same_answer = dataset_merged #dataset_merged[dataset_merged["Answer"].notna()]
same_answer = same_answer.groupby(["Question + Subquestion", "Answer"])["Respondent ID"].nunique().reset_index()
same_answer.rename(columns={"Respondent ID":"Same Answer"}, inplace=True)
same_answer

Out[ ]:

	Question + Subquestion	Answer	Same Answer
0	Question 1-Response	Answer 1	14
1	Question 1-Response	Answer 2	10
2	Question 1-Response	Answer 3	13
3	Question 1-Response	Answer 4	17
4	Question 1-Response	Answer 5	22
...	...	...	...
683	Question 9-Response 4	Answer 4	16
684	Question 9-Response 4	Answer 5	13
685	Question 9-Response 4	Answer 6	14
686	Question 9-Response 4	Answer 7	12
687	Question 9-Response 4	Answer 8	19

688 rows × 3 columns

In [ ]:

dataset_merged_three = pd.merge(left=dataset_merged_two, right=same_answer, how="left", left_on=["Question + Subquestion", "Answer"], right_on=["Question + Subquestion", "Answer"])
dataset_merged_three["Same Answer"].fillna(0, inplace=True)
print("Original Data", len(dataset_merged_two))
print("Merged Data", len(dataset_merged_three))
dataset_merged_three

Original Data 17028
Merged Data 17028

Out[ ]:

	Respondent ID	Identify which division you work in.-Response	Identify which division you work in.-Other (please specify)	Which of the following best describes your position level?-Response	Which generation are you apart of?-Response	Please select the gender in which you identify.-Response	Which duration range best aligns with your tenure at your company?-Response	Which of the following best describes your employment type?-Response	Question + Subquestion	Answer	Question	Respondents	Same Answer
0	5379192392	Infrastructure	NaN	Staff	Generation X (born between 1965-1980)	Male	0-2 years	Full time Employee	Question 1-Response	NaN	Question 1	119	0.0
1	2658722536	Finance	NaN	Staff	NaN	NaN	10+ years	Full time Employee	Question 1-Response	Answer 4	Question 1	119	17.0
2	4044163394	Infrastructure	NaN	Department Lead	Generation X (born between 1965-1980)	Male	3-5 years	Full time Employee	Question 1-Response	Answer 5	Question 1	119	22.0
3	5535865599	Infrastructure	NaN	Manager	Millennial (born between 1981-2000)	Non-Binary	5-10 years	Full time Employee	Question 1-Response	Answer 1	Question 1	119	14.0
4	3356802928	Port Operations	NaN	Manager	Generation X (born between 1965-1980)	Female	10+ years	Full time Employee	Question 1-Response	NaN	Question 1	119	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...
17023	7940065082	Infrastructure	NaN	Department Lead	Baby Boomer (born between 1946-1964)	Male	10+ years	Full time Employee	Question 30-Response 3	Answer 8	Question 30	182	14.0
17024	5157705612	Finance	NaN	Staff	Millennial (born between 1981-2000)	Female	5-10 years	Full time Employee	Question 30-Response 3	Answer 6	Question 30	182	20.0
17025	9920755555	Port Operations	NaN	Staff	Millennial (born between 1981-2000)	Female	3-5 years	Full time Employee	Question 30-Response 3	NaN	Question 30	182	0.0
17026	6638341389	Infrastructure	NaN	Manager	Millennial (born between 1981-2000)	Female	3-5 years	Full time Employee	Question 30-Response 3	NaN	Question 30	182	0.0
17027	8114622230	Information Technology	NaN	Staff	Prefer not to answer	Male	5-10 years	Full time Employee	Question 30-Response 3	NaN	Question 30	182	0.0

17028 rows × 13 columns

In [ ]:

output = dataset_merged_three.copy()
output.rename(columns={"Identify which division you work in.-Response":"Division Primary", "Identify which division you work in.-Other (please specify)":"Division Secondary", 
                       "Which of the following best describes your position level?-Response":"Position", "Which generation are you apart of?-Response":"Generation", 
                       "Please select the gender in which you identify.-Response":"Gender", "Which duration range best aligns with your tenure at your company?-Response":"Tenure", 
                       "Which of the following best describes your employment type?-Response":"Employment Type"}, inplace=True)
output

Out[ ]:

	Respondent ID	Division Primary	Division Secondary	Position	Generation	Gender	Tenure	Employment Type	Question + Subquestion	Answer	Question	Respondents	Same Answer
0	5379192392	Infrastructure	NaN	Staff	Generation X (born between 1965-1980)	Male	0-2 years	Full time Employee	Question 1-Response	NaN	Question 1	119	0.0
1	2658722536	Finance	NaN	Staff	NaN	NaN	10+ years	Full time Employee	Question 1-Response	Answer 4	Question 1	119	17.0
2	4044163394	Infrastructure	NaN	Department Lead	Generation X (born between 1965-1980)	Male	3-5 years	Full time Employee	Question 1-Response	Answer 5	Question 1	119	22.0
3	5535865599	Infrastructure	NaN	Manager	Millennial (born between 1981-2000)	Non-Binary	5-10 years	Full time Employee	Question 1-Response	Answer 1	Question 1	119	14.0
4	3356802928	Port Operations	NaN	Manager	Generation X (born between 1965-1980)	Female	10+ years	Full time Employee	Question 1-Response	NaN	Question 1	119	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...
17023	7940065082	Infrastructure	NaN	Department Lead	Baby Boomer (born between 1946-1964)	Male	10+ years	Full time Employee	Question 30-Response 3	Answer 8	Question 30	182	14.0
17024	5157705612	Finance	NaN	Staff	Millennial (born between 1981-2000)	Female	5-10 years	Full time Employee	Question 30-Response 3	Answer 6	Question 30	182	20.0
17025	9920755555	Port Operations	NaN	Staff	Millennial (born between 1981-2000)	Female	3-5 years	Full time Employee	Question 30-Response 3	NaN	Question 30	182	0.0
17026	6638341389	Infrastructure	NaN	Manager	Millennial (born between 1981-2000)	Female	3-5 years	Full time Employee	Question 30-Response 3	NaN	Question 30	182	0.0
17027	8114622230	Information Technology	NaN	Staff	Prefer not to answer	Male	5-10 years	Full time Employee	Question 30-Response 3	NaN	Question 30	182	0.0

17028 rows × 13 columns

In [ ]:

output.columns

Out[ ]:

Index(['Respondent ID', 'Identify which division you work in.-Response',
       'Identify which division you work in.-Other (please specify)',
       'Which of the following best describes your position level?-Response',
       'Which generation are you apart of?-Response',
       'Please select the gender in which you identify.-Response',
       'Which duration range best aligns with your tenure at your company?-Response',
       'Which of the following best describes your employment type?-Response',
       'Question + Subquestion', 'Answer', 'Question', 'Respondents',
       'Same Answer'],
      dtype='object')

In [ ]:

output.to_excel("Final_Output.xlsx", index=False)

In [ ]:

'Python' 카테고리의 다른 글

python) seaborn(sns) scatterplot 그래프 색상 지정하기 (0)	2022.06.27
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x81 in position 17: invalid start byte (0)	2022.06.27
Resample, 시간대, 월, 년, 일별 데이터 값 계산 (0)	2022.04.28
Colab) Wordcloud 한글이 보이지 않을 때, 워드클라우드 만들기, 주피터 노트북, R프로그램 KoNLP 설치 실패. 워드 클라우드 저장하는 코드 (0)	2022.04.25
[colab] mp3 두 개 합치기/mov -> mp4 -> wav /audiodisplay (0)	2022.04.23

현재글python survey data anaylsis - html to tistory

I am happy because I am learning

texteditor, jupyternotebook, 파이썬에러, chatbot, Python, 티스토리관리, crontab, 워드프레스, ubuntu, dataanalysis, OOP, excel, 정보처리기사, 글또, NLP, pandas, Udemy, 정보처리기사실기, pytorch, chromedriver,

내 블로그 - 관리자 홈 전환	`Q` `Q`
새 글 쓰기	`W` `W`

글 수정 (권한 있는 경우)	`E` `E`
댓글 영역으로 이동	`C` `C`

이 페이지의 URL 복사	`S` `S`
맨 위로 이동	`T` `T`
티스토리 홈 이동	`H` `H`
단축키 안내	`Shift` + `/` `⇧` + `/`

Summerorange

python survey data anaylsis - html to tistory

Bring Data¶

Data copy¶

'Python' 카테고리의 다른 글

'Python'의 다른글

티스토리툴바

개인정보

단축키

내 블로그

블로그 게시글

모든 영역

2025. 04
일	월	화	수	목	금	토
		1	2	3	4	5
6	7	8	9	10	11	12
13	14	15	16	17	18	19
20	21	22	23	24	25	26
27	28	29	30

python survey data anaylsis - html to tistory

Bring Data¶

Data copy¶

'Python' 카테고리의 다른 글

'Python'의 다른글

관련글

티스토리툴바

개인정보

단축키

내 블로그

블로그 게시글

모든 영역