In [1]:

    

%run "../Functions/4. User comparison.ipynb"


    

    




rmdf152 read_csv success






    




../Utilities/Preparation.ipynb:2: ParserWarning: Both a converter and dtype were specified for column customData.localplayerguid - only the converter will be used
  "cells": [






    




gformEN read_csv success
gformFR read_csv success
temporalities set

In [2]:

    

# Rename columns of the Google Forms table with tags independantly of form language
columnTags = ["timestamp", "gameInterest", "gameFrequency", "age", "gender", "biologyStudy", "biologyInterest", "synthBioKnowledge", "biobrickKnowledge", "previousVersion", "previousPlay", "arcadePlay", "androidPlay", "Q1", "Q2", "Q3", "Q4", "Q5", "Q6", "Q7", "Q8", "Q9", "Q10", "Q11", "Q12", "Q13", "Q14", "Q15", "Q16", "Q17", "Q18", "Q19", "Q20", "Q21", "Q22", "Q23", "Q24", "Q25", "Q26", "Q27", "comments", "anonymousID", "lang", "temporality"]
columnQuestions = gform.columns.values.tolist()
googleData = gform.rename(columns=dict(zip(columnQuestions, columnTags)))
#googleData.head()


    

In [3]:

    

# Replaces answers to scientific questions in the questionnaires by their values (True or False)
correctedData = googleData.copy()
for rowId in range(correctedData.shape[0]):
    # Get the correction for each subject
    playerId = correctedData.loc[rowId, "anonymousID"]
    correction = getCorrections(playerId)
    if correction.shape[1] > 0:
        # If subject has answered questionnaire
        correction = correction.rename(index=dict(zip(columnQuestions, columnTags)))
        # Replace scientific answers by their correction
        for questionId in range(27):
            questionTag = "Q" + str(questionId + 1)
            correctedData.loc[rowId, questionTag] = int(correction.loc[questionTag, "corrections" + str(rowId)])
    
#correctedData.tail(15)


    

In [4]:

    

list(zip(columnQuestions, columnTags))


    

    
Out[4]:





[('Timestamp', 'timestamp'),
 ('Are you interested in video games?', 'gameInterest'),
 ('Do you play video games?', 'gameFrequency'),
 ('How old are you?', 'age'),
 ('What is your gender?', 'gender'),
 ('How long have you studied biology?', 'biologyStudy'),
 ('Are you interested in biology?', 'biologyInterest'),
 ('Before playing Hero.Coli, had you ever heard about synthetic biology?',
  'synthBioKnowledge'),
 ('Before playing Hero.Coli, had you ever heard about BioBricks?',
  'biobrickKnowledge'),
 ('Have you ever played an older version of Hero.Coli before?',
  'previousVersion'),
 ('Have you played the current version of Hero.Coli?', 'previousPlay'),
 ('Have you played the arcade cabinet version of Hero.Coli?', 'arcadePlay'),
 ('Have you played the Android version of Hero.Coli?', 'androidPlay'),
 ('In order to modify the abilities of the bacterium, you have to...', 'Q1'),
 ('What are BioBricks and devices?', 'Q2'),
 ('What is the name of this BioBrick? TER', 'Q3'),
 ('What is the name of this BioBrick? PR', 'Q4'),
 ('What is the name of this BioBrick? CDS', 'Q5'),
 ('What is the name of this BioBrick? RBS', 'Q6'),
 ('What does this BioBrick do? TER', 'Q7'),
 ('What does this BioBrick do? PR', 'Q8'),
 ('What does this BioBrick do? CDS', 'Q9'),
 ('What does this BioBrick do? RBS', 'Q10'),
 ('Pick the case where the BioBricks are well-ordered:', 'Q11'),
 ('When does green fluorescence happen?', 'Q12'),
 ('What happens when you unequip the movement device?', 'Q13'),
 ('What is this? PLASMID', 'Q14'),
 ('What does this device do? PCONS:RBS:GFP:TER', 'Q15'),
 ('What does this device do? PCONS:RBS:FLHDC:TER', 'Q16'),
 ('What does this device do? PCONS:RBS:AMPR:TER', 'Q17'),
 ('What does this device do? PBAD:RBS:GFP:TER', 'Q18'),
 ('What does this device do? PCONS:RBS:GFP:TER 2', 'Q19'),
 ('What does this device do? PCONS:RBS:FLHDC:TER 2', 'Q20'),
 ('What does this device do? PCONS:RBS:AMPR:TER 2', 'Q21'),
 ('What does this device do? PBAD:RBS:GFP:TER 2', 'Q22'),
 ('Guess: what would a device producing l-arabinose do, if it started with a l-arabinose-induced promoter?',
  'Q23'),
 ('Guess: the bacterium would glow yellow...', 'Q24'),
 ('What is the species of the bacterium of the game?', 'Q25'),
 ('What is the scientific name of the tails of the bacterium?', 'Q26'),
 ('Find the antibiotic:', 'Q27'),
 ('You can write down remarks here.', 'comments'),
 ('Do not edit -  pre-filled anonymous ID', 'anonymousID'),
 ('Language', 'lang'),
 ('Temporality', 'temporality')]

In [5]:

    

# Get only answers to scientific questions
correctedScientific = correctedData.loc[:, "Q1":"Q27"]
#correctedScientific.head()


    

In [6]:

    

# Remove timestamp and comments features
codedData = googleData.copy().drop(['timestamp', "comments"], axis=1)
codedData.head()


    

    
Out[6]:







  

    

      

      
gameInterest
      
gameFrequency
      
age
      
gender
      
biologyStudy
      
biologyInterest
      
synthBioKnowledge
      
biobrickKnowledge
      
previousVersion
      
previousPlay
      
...
      
Q21
      
Q22
      
Q23
      
Q24
      
Q25
      
Q26
      
Q27
      
anonymousID
      
lang
      
temporality
    
  
  

    

      
0
      
Extremely
      
Extremely
      
23
      
Female
      
Until bachelor's degree
      
Extremely
      
Yes
      
NaN
      
No
      
Yes
      
...
      
It generates antibiotic resistance
      
It generates green fluorescence in presence of...
      
After being induced, it would produce more and...
      
I don't know
      
E. Coli
      
Flagella
      
Ampicillin
      
8d352896-a3f1-471c-8439-0f426df901c1
      
en
      
before
    
    

      
1
      
Moderately
      
Moderately
      
28
      
Other
      
Until the end of high school
      
Moderately
      
Yes
      
NaN
      
No
      
Yes
      
...
      
It generates antibiotic resistance
      
It generates green fluorescence in presence of...
      
After being induced, it would produce more and...
      
I don't know
      
E. Coli
      
Flagella
      
Ampicillin
      
7037c5b2-c286-498e-9784-9a061c778609
      
en
      
after
    
    

      
2
      
A lot
      
Moderately
      
20
      
Female
      
Until bachelor's degree
      
Moderately
      
No
      
NaN
      
No
      
Yes
      
...
      
It generates antibiotic resistance
      
It generates green fluorescence
      
I don't know
      
If it produces BFP under purple light
      
E. Coli
      
Flagella
      
Ampicillin
      
5c4939b5-425b-4d19-b5d2-0384a515539e
      
en
      
after
    
    

      
3
      
Moderately
      
Moderately
      
21
      
Male
      
Until bachelor's degree
      
A lot
      
Yes
      
NaN
      
No
      
Yes
      
...
      
It generates antibiotic resistance
      
It generates green fluorescence in presence of...
      
After being induced, it would produce more and...
      
If it produces YFP under cyan light
      
E. Coli
      
Flagella
      
Ampicillin
      
acb9c989-b4a6-4c4d-81cc-6b5783ec71d8
      
en
      
before
    
    

      
4
      
Moderately
      
Rarely
      
18
      
Female
      
Until bachelor's degree
      
A lot
      
No
      
No
      
No
      
No
      
...
      
I don't know
      
I don't know
      
I don't know
      
If it produced YFP under cyan light
      
I don't know
      
I don't know
      
Ampicillin
      
1a03bc9e-bed4-4ddd-be7f-af23b1d5eb65
      
en
      
before
    
  

5 rows × 42 columns

In [7]:

    

# Code answers with integers when possible

# Define equivalences
# gameInterest
gameInterestCoding = {"A lot": 4, "Beaucoup": 4, "Enormément": 5, "Extremely": 5, "Moderately": 3, "Moyennement": 3, "Slightly": 2, "Un peu": 2, "I don't know": 3, "Je ne sais pas": 3, "Not at all": 1, "Pas du tout": 1}
# gameFrequency
gameFrequencyCoding = {"A lot": 4, "Beaucoup": 4, "Enormément": 5, "Extremely": 5, "Moderately": 3, "Moyennement": 3, "Rarely": 2, "Un peu": 2, "I don't know": 3, "Je ne sais pas": 3, "Not at all": 1, "Pas du tout": 1}
# biologyStudy
biologyStudyCoding = {"Not even in middle school": 0, "Jamais": 0, "Jamais, pas même au collège": 0, "Until the end of middle school": 1, "Jusqu'au brevet": 1, "Until the end of high school": 2, "Jusqu'au bac": 2, "Until bachelor's degree": 3, "Jusqu'à la license": 3, "At least until master's degree": 4, "Au moins jusqu'au master": 4, "I don't know": 0, "Je ne sais pas": 0}
# biologyInterest
biologyInterestCoding = {"A lot": 4, "Beaucoup": 4, "Enormément": 5, "Extremely": 5, "Moderately": 3, "Moyennement": 3, "Slightly": 2, "Un peu": 2, "I don't know": 3, "Je ne sais pas": 3, "Not at all": 1, "Pas du tout": 1}
# synthBioKnowledge
# biobrickKnowledge
previousKnowledgeCoding = {"Yes": 1, "No": 0, "I don't know": 0, "Oui": 1, 'Non': 0, "Je ne sais pas": 0}
# previousVersion
# previousPlay
# arcadePlay
# androidPlay
previousPlayCoding = {"Multiple times": 3, "A few times": 2, "Once": 1, "Yes": 1, "No": 0, "I don't know": 0, "De nombreuses fois": 3, "Quelques fois": 2, "Une fois": 1, "Oui": 1, "Non": 0, "Je ne sais pas": 0}
# lang
languageCoding = {"en": 0, "fr": 1}
# temporality
temporalityCoding = {"before": 0, "after": 1, "undefined": -5}

# Fill NaN cells
codedData["biobrickKnowledge"].fillna("I don't know", inplace = True)
codedData["arcadePlay"].fillna("I don't know", inplace = True)
codedData["androidPlay"].fillna("I don't know", inplace = True)
codedData["previousPlay"].fillna("I don't know", inplace = True)

# Replace by code
for rowId in range(codedData.shape[0]):
    codedData.loc[rowId, "gameInterest"] = gameInterestCoding[codedData.loc[rowId, "gameInterest"]]
    codedData.loc[rowId, "gameFrequency"] = gameFrequencyCoding[codedData.loc[rowId, "gameFrequency"]]
    codedData.loc[rowId, "biologyStudy"] = biologyStudyCoding[codedData.loc[rowId, "biologyStudy"]]
    codedData.loc[rowId, "biologyInterest"] = biologyInterestCoding[codedData.loc[rowId, "biologyInterest"]]
    codedData.loc[rowId, "synthBioKnowledge"] = previousKnowledgeCoding[codedData.loc[rowId, "synthBioKnowledge"]]
    codedData.loc[rowId, "biobrickKnowledge"] = previousKnowledgeCoding[codedData.loc[rowId, "biobrickKnowledge"]]
    codedData.loc[rowId, "previousVersion"] = previousPlayCoding[codedData.loc[rowId, "previousVersion"]]
    codedData.loc[rowId, "previousPlay"] = previousPlayCoding[codedData.loc[rowId, "previousPlay"]]
    codedData.loc[rowId, "arcadePlay"] = previousPlayCoding[codedData.loc[rowId, "arcadePlay"]]
    codedData.loc[rowId, "androidPlay"] = previousPlayCoding[codedData.loc[rowId, "androidPlay"]]
    codedData.loc[rowId, "lang"] = languageCoding[codedData.loc[rowId, "lang"]]
    codedData.loc[rowId, "temporality"] = temporalityCoding[codedData.loc[rowId, "temporality"]]


    

In [8]:

    

# One-Hot version
codedData = pd.get_dummies(codedData, prefix = ["gender", "Q1", "Q2", "Q3", "Q4", "Q5", "Q6", "Q7", "Q8", "Q9", "Q10", "Q11", "Q12", "Q13", "Q14", "Q15", "Q16", "Q17", "Q18", "Q19", "Q20", "Q21", "Q22", "Q23", "Q24", "Q25", "Q26", "Q27"], columns = ["gender", "Q1", "Q2", "Q3", "Q4", "Q5", "Q6", "Q7", "Q8", "Q9", "Q10", "Q11", "Q12", "Q13", "Q14", "Q15", "Q16", "Q17", "Q18", "Q19", "Q20", "Q21", "Q22", "Q23", "Q24", "Q25", "Q26", "Q27"])
#codedData.head()


    

In [9]:

    

# Split the forms according to temporality
beforeForms = codedData.copy().loc[codedData["temporality"] == 0,:]
afterForms = codedData.copy().loc[codedData["temporality"] == 1,:]
undefForms = codedData.copy().loc[codedData["temporality"] == -5,:]
defForms = codedData.copy().loc[codedData["temporality"] >= 0,:] # Either before or after
# For subjects with both before and after forms, join the two
beforeAndAfterForms = pd.merge(beforeForms, afterForms, on="anonymousID", suffixes=('_before', '_after'))
#beforeForms.head()
#afterForms.head()
#undefForms.head()
#defForms.head()
#beforeAndAfterForms.head()


    

In [10]:

    

# Remove ID feature
allForms = codedData.copy().drop("anonymousID", axis=1)
beforeForms.drop("anonymousID", axis=1, inplace = True)
afterForms.drop("anonymousID", axis=1, inplace = True)
undefForms.drop("anonymousID", axis=1, inplace = True)
defForms.drop("anonymousID", axis=1, inplace = True)
beforeAndAfterForms.drop("anonymousID", axis=1, inplace = True)


    

In [11]:

    

# Remove timestamp and comments features
codedCorrectedData = correctedData.copy().drop(['timestamp', "comments"], axis=1)


    

In [12]:

    

# Fill NaN cells
codedCorrectedData["biobrickKnowledge"].fillna("I don't know", inplace = True)
codedCorrectedData["arcadePlay"].fillna("I don't know", inplace = True)
codedCorrectedData["androidPlay"].fillna("I don't know", inplace = True)
codedCorrectedData["previousPlay"].fillna("I don't know", inplace = True)

# Replace by code
for rowId in range(codedData.shape[0]):
    codedCorrectedData.loc[rowId, "gameInterest"] = gameInterestCoding[codedCorrectedData.loc[rowId, "gameInterest"]]
    codedCorrectedData.loc[rowId, "gameFrequency"] = gameFrequencyCoding[codedCorrectedData.loc[rowId, "gameFrequency"]]
    codedCorrectedData.loc[rowId, "biologyStudy"] = biologyStudyCoding[codedCorrectedData.loc[rowId, "biologyStudy"]]
    codedCorrectedData.loc[rowId, "biologyInterest"] = biologyInterestCoding[codedCorrectedData.loc[rowId, "biologyInterest"]]
    codedCorrectedData.loc[rowId, "synthBioKnowledge"] = previousKnowledgeCoding[codedCorrectedData.loc[rowId, "synthBioKnowledge"]]
    codedCorrectedData.loc[rowId, "biobrickKnowledge"] = previousKnowledgeCoding[codedCorrectedData.loc[rowId, "biobrickKnowledge"]]
    codedCorrectedData.loc[rowId, "previousVersion"] = previousPlayCoding[codedCorrectedData.loc[rowId, "previousVersion"]]
    codedCorrectedData.loc[rowId, "previousPlay"] = previousPlayCoding[codedCorrectedData.loc[rowId, "previousPlay"]]
    codedCorrectedData.loc[rowId, "arcadePlay"] = previousPlayCoding[codedCorrectedData.loc[rowId, "arcadePlay"]]
    codedCorrectedData.loc[rowId, "androidPlay"] = previousPlayCoding[codedCorrectedData.loc[rowId, "androidPlay"]]
    codedCorrectedData.loc[rowId, "lang"] = languageCoding[codedCorrectedData.loc[rowId, "lang"]]
    codedCorrectedData.loc[rowId, "temporality"] = temporalityCoding[codedCorrectedData.loc[rowId, "temporality"]]


    

In [13]:

    

# One-Hot versions of the above dataframes
codedCorrectedData = pd.get_dummies(codedCorrectedData, prefix = ["gender"], columns = ["gender"])
codedCorrectedData.head()


    

    
Out[13]:







  

    

      

      
gameInterest
      
gameFrequency
      
age
      
biologyStudy
      
biologyInterest
      
synthBioKnowledge
      
biobrickKnowledge
      
previousVersion
      
previousPlay
      
arcadePlay
      
...
      
Q25
      
Q26
      
Q27
      
anonymousID
      
lang
      
temporality
      
gender_Female
      
gender_Male
      
gender_Other
      
gender_Prefer not to say
    
  
  

    

      
0
      
5
      
5
      
23
      
3
      
5
      
1
      
0
      
0
      
1
      
0
      
...
      
1
      
1
      
1
      
8d352896-a3f1-471c-8439-0f426df901c1
      
0
      
0
      
1
      
0
      
0
      
0
    
    

      
1
      
3
      
3
      
28
      
2
      
3
      
1
      
0
      
0
      
1
      
0
      
...
      
1
      
1
      
1
      
7037c5b2-c286-498e-9784-9a061c778609
      
0
      
1
      
0
      
0
      
1
      
0
    
    

      
2
      
4
      
3
      
20
      
3
      
3
      
0
      
0
      
0
      
1
      
0
      
...
      
1
      
1
      
1
      
5c4939b5-425b-4d19-b5d2-0384a515539e
      
0
      
1
      
1
      
0
      
0
      
0
    
    

      
3
      
3
      
3
      
21
      
3
      
4
      
1
      
0
      
0
      
1
      
0
      
...
      
1
      
1
      
1
      
acb9c989-b4a6-4c4d-81cc-6b5783ec71d8
      
0
      
0
      
0
      
1
      
0
      
0
    
    

      
4
      
3
      
2
      
18
      
3
      
4
      
0
      
0
      
0
      
0
      
0
      
...
      
0
      
0
      
1
      
1a03bc9e-bed4-4ddd-be7f-af23b1d5eb65
      
0
      
0
      
1
      
0
      
0
      
0
    
  

5 rows × 45 columns

In [14]:

    

# Split the forms according to temporality
beforeCorrectedForms = codedCorrectedData.copy().loc[codedCorrectedData["temporality"] == 0,:]
afterCorrectedForms = codedCorrectedData.copy().loc[codedCorrectedData["temporality"] == 1,:]
undefCorrectedForms = codedCorrectedData.copy().loc[codedCorrectedData["temporality"] == -5,:]
defCorrectedForms = codedCorrectedData.copy().loc[codedCorrectedData["temporality"] >= 0,:] # Either before or after
# For subjects with both before and after forms, join the two
beforeAndAfterCorrectedForms = pd.merge(beforeCorrectedForms, afterCorrectedForms, on="anonymousID", suffixes=('_before', '_after'))
#beforeCorrectedForms.head()
#afterCorrectedForms.head()
#undefCorrectedForms.head()
#defCorrectedForms.head()
#beforeAndAfterCorrectedForms.head()


    

In [15]:

    

# Remove ID feature
allCorrectedForms = codedCorrectedData.copy().drop("anonymousID", axis=1)
beforeCorrectedForms.drop("anonymousID", axis=1, inplace = True)
afterCorrectedForms.drop("anonymousID", axis=1, inplace = True)
undefCorrectedForms.drop("anonymousID", axis=1, inplace = True)
defCorrectedForms.drop("anonymousID", axis=1, inplace = True)
beforeAndAfterCorrectedForms.drop("anonymousID", axis=1, inplace = True)


    

In [16]:

    

# Use defForms and defCorrectedForms for coded data


    

In [17]:

    

# Fetch RedMetrics data for subjects which answered the gform
allData = getAllUserVectorData(getAllResponders(), _source=[])


    

    






 
 










    




C:\Users\Mikael\Anaconda3\envs\conda-env-python3-py\lib\site-packages\ipykernel_launcher.py:9: FutureWarning: using a dict on a Series for aggregation
is deprecated and will be removed in a future version
  if __name__ == '__main__':

In [18]:

    

# Put subjects as rows and features as columns
allData = allData.transpose()
allData.head()


    

    
Out[18]:







  

    

      

      
sessionsCount
      
scorebefore
      
scoreafter
      
scoreundefined
      
complete
      
configure
      
craft
      
death
      
equip
      
unequip
      
...
      
5
      
6
      
7
      
8
      
9
      
10
      
11
      
12
      
13
      
14
    
  
  

    

      
8d352896-a3f1-471c-8439-0f426df901c1
      
1.0
      
18.0
      
NaN
      
NaN
      
0.0
      
0.0
      
5.0
      
5.0
      
16.0
      
1.0
      
...
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
    
    

      
7037c5b2-c286-498e-9784-9a061c778609
      
2.0
      
NaN
      
22.0
      
NaN
      
2.0
      
0.0
      
45.0
      
25.0
      
3.0
      
4.0
      
...
      
3.686890e+02
      
1.333480e+02
      
1.753140e+02
      
1.830370e+02
      
5.475110e+02
      
1.582290e+02
      
6.438000e+00
      
2.750300e+01
      
1.550830e+02
      
1.422350e+02
    
    

      
5c4939b5-425b-4d19-b5d2-0384a515539e
      
1.0
      
NaN
      
15.0
      
NaN
      
0.0
      
0.0
      
7.0
      
11.0
      
25.0
      
3.0
      
...
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
    
    

      
acb9c989-b4a6-4c4d-81cc-6b5783ec71d8
      
1.0
      
23.0
      
NaN
      
NaN
      
0.0
      
1.0
      
11.0
      
11.0
      
16.0
      
3.0
      
...
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
      
9.223372e+09
    
    

      
1a03bc9e-bed4-4ddd-be7f-af23b1d5eb65
      
1.0
      
3.0
      
NaN
      
NaN
      
0.0
      
1.0
      
10.0
      
118.0
      
133.0
      
7.0
      
...
      
6.856270e+02
      
4.544890e+02
      
1.379500e+02
      
2.749810e+02
      
5.320300e+01
      
6.418300e+01
      
3.634000e+00
      
4.095000e+00
      
9.223372e+09
      
9.223372e+09
    
  

5 rows × 40 columns

In [19]:

    

# Drop useless columns in which all rows have the same value
allData.drop(["switch", "gotomooc"], axis=1, inplace = True)
# Fill NaN with negatives
allData.fillna(-1, inplace = True)


    

In [20]:

    

# Get the subset of subjects who have answered before and after
fullProcessData = allData[allData["scorebefore"] >= 0]
fullProcessData = fullProcessData[fullProcessData["scoreafter"] >= 0]
#fullProcessData.loc["01e85778-2903-447b-bbab-dd750564ee2d",:]


    

In [21]:

    

#Get the subset of subjects who have answered the after questionnaire
withAfterData = allData.copy()[allData["scoreafter"] >= 0]
withAfterData['anonymousID'] = withAfterData.index
withAfterData['anonymousID'] = withAfterData['anonymousID'].apply(lambda x: x.strip('"'))
# Join with questionnaire data with complete answers
afterNotCorrected = codedData.copy().loc[codedData["temporality"] == 1,:]
gameAndAfterData = pd.merge(withAfterData, afterNotCorrected, on="anonymousID")
gameAndAfterData.drop("anonymousID", axis=1, inplace = True)
#Join with questionnaire data with corrected answers
afterCorrected = codedCorrectedData.copy().loc[codedCorrectedData["temporality"] == 1,:]
gameAndCorrectedAfterData = pd.merge(withAfterData, afterCorrected, on="anonymousID")
gameAndCorrectedAfterData.drop("anonymousID", axis=1, inplace = True)
#gameAndAfterData.head()
#gameAndCorrectedAfterData.head()


    

In [22]:

    

allDataClassif = allData.copy()
allDataClassif['anonymousID'] = allData.index
allDataClassif['anonymousID'] = allDataClassif['anonymousID'].apply(lambda x: x.strip('"'))

# If checkpoint not reached, set time to 3600 (1h)
def floorCheckpoints(value):
    if value > 3600:
        return 3600
    return value
for col in allDataClassif.columns.values.tolist():
    if isinstance(col, np.int64):
        allDataClassif[col] = allDataClassif[col].apply(floorCheckpoints)
allDataClassif["completionTime"] = allDataClassif["completionTime"].apply(lambda x: min(x, 7200))        

# floor thoroughness
allDataClassif["thoroughness"]  = allDataClassif["thoroughness"].apply(lambda x: min(x, 1000))


    

In [23]:

    

#Join with questionnaire data with corrected answers
gameAndCorrectedAfterDataClassif = pd.merge(withAfterData, afterCorrected, on="anonymousID")
gameAndCorrectedAfterDataClassif['anonymousID'] = gameAndCorrectedAfterDataClassif['anonymousID'].apply(lambda x: x.strip('"'))
gameAndCorrectedAfterDataClassif.drop(["scorebefore", "scoreundefined", "temporality"], axis=1, inplace = True)

for col in gameAndCorrectedAfterDataClassif.columns.values.tolist():
    if isinstance(col, np.int64):
        gameAndCorrectedAfterDataClassif[col] = gameAndCorrectedAfterDataClassif[col].apply(floorCheckpoints)
gameAndCorrectedAfterDataClassif["completionTime"] = gameAndCorrectedAfterDataClassif["completionTime"].apply(lambda x: min(x, 7200))

# floor thoroughness
gameAndCorrectedAfterDataClassif["thoroughness"]  = gameAndCorrectedAfterDataClassif["thoroughness"].apply(lambda x: min(x, 1000))


    

In [24]:

    

#Get the subset of subjects who have answered the before questionnaire
withBeforeData = allData.copy()[allData["scorebefore"] >= 0]
withBeforeData['anonymousID'] = withBeforeData.index
withBeforeData['anonymousID'] = withBeforeData['anonymousID'].apply(lambda x: x.strip('"'))
beforeCorrected = codedCorrectedData.copy().loc[codedCorrectedData["temporality"] == 0,:]
#Join with questionnaire data with corrected answers
gameAndCorrectedBeforeDataClassif = pd.merge(withBeforeData, beforeCorrected, on="anonymousID")
gameAndCorrectedBeforeDataClassif['anonymousID'] = gameAndCorrectedBeforeDataClassif['anonymousID'].apply(lambda x: x.strip('"'))
gameAndCorrectedBeforeDataClassif.drop(["scoreafter", "scoreundefined", "temporality"], axis=1, inplace = True)

# If checkpoint not reached, set time to 3600 (1h)
for col in gameAndCorrectedBeforeDataClassif.columns.values.tolist():
    if isinstance(col, np.int64):
        gameAndCorrectedBeforeDataClassif[col] = gameAndCorrectedBeforeDataClassif[col].apply(floorCheckpoints)
gameAndCorrectedBeforeDataClassif["completionTime"] = gameAndCorrectedBeforeDataClassif["completionTime"].apply(lambda x: min(x, 7200))

# floor thoroughness
gameAndCorrectedBeforeDataClassif["thoroughness"]  = gameAndCorrectedBeforeDataClassif["thoroughness"].apply(lambda x: min(x, 1000))


    

In [ ]:

    




    

In [ ]:

    




    

In [ ]: