notebook.community

Edit and run 





In [1]:



    


%run dataFormating.ipynb



    


















    






rmdfTestUsers read_csv success (1/3)
rmdf1522 read_csv success (2/3)
rmdf160 read_csv success (3/3)
gform read_csv success
gformFR read_csv success
temporalities set (user answer method)










    






 
 















    






 
 















    






profile info set










    






 
 















    






dataFormating.ipynb:16: FutureWarning: pd.TimeGrouper is deprecated and will be removed; Please use pd.Grouper(freq=...)
  "metadata": {},
dataFormating.ipynb:16: FutureWarning: using a dict on a Series for aggregation
is deprecated and will be removed in a future version
  "metadata": {},

What subsets of scientific questions tend to be answered correctly by the same subjects?

Mining





In [2]:



    


from orangecontrib.associate.fpgrowth import *  
import pandas as pd
from numpy import *



    











In [3]:



    


questions = correctedScientific.columns
correctedScientificText = [[] for _ in range(correctedScientific.shape[0])]
for q in questions:
    for index in range(correctedScientific.shape[0]):
        r = correctedScientific.index[index]
        if correctedScientific.loc[r, q]:
            correctedScientificText[index].append(q)
#correctedScientificText



    











In [4]:



    


len(correctedScientificText)



    


















    
Out[4]:








252

















In [5]:



    


# Get frequent itemsets with support > 25%
# run time < 1 min
support = 0.20
itemsets = frequent_itemsets(correctedScientificText, math.floor(len(correctedScientificText) * support))
#dict(itemsets)



    











In [6]:



    


# Generate rules according to confidence, confidence > 85 %
# run time < 5 min
confidence = 0.80
rules = association_rules(dict(itemsets), confidence)
#list(rules)



    











In [7]:



    


# Transform rules generator into a Dataframe
rulesDataframe = pd.DataFrame([(ant, cons, supp, conf) for ant, cons, supp, conf in rules])
rulesDataframe.rename(columns = {0:"antecedants", 1:"consequents", 2:"support", 3:"confidence"}, inplace=True)
rulesDataframe.head()



    


















    
Out[7]:











  
    

      
      antecedants
      consequents
      support
      confidence
    

  
  
    

      0
      (QDeviceRbsPconsAmprTer, QDeviceGfpRbsPconsTer...
      (QDeviceRbsPconsFlhdcTer)
      52
      1.000000
    

    

      1
      (QDeviceGfpRbsPconsTer, QGenotypePhenotype)
      (QDeviceRbsPconsFlhdcTer, QDeviceRbsPconsAmprTer)
      52
      0.962963
    

    

      2
      (QGenotypePhenotype, QDeviceRbsPconsAmprTer)
      (QDeviceRbsPconsFlhdcTer, QDeviceGfpRbsPconsTer)
      52
      0.866667
    

    

      3
      (QDeviceRbsPconsFlhdcTer, QDeviceRbsPconsAmprT...
      (QDeviceGfpRbsPconsTer)
      52
      0.881356
    

    

      4
      (QDeviceRbsPconsFlhdcTer, QDeviceGfpRbsPconsTe...
      (QGenotypePhenotype)
      52
      0.896552
    

  




















In [8]:



    


# Save the mined rules to file
rulesDataframe.to_csv("results/associationRulesMiningSupport"+str(support)+"percentsConfidence"+str(confidence)+"percents.csv")

Search for interesting rules

Interesting rules are more likely to be the ones with highest confidence, the highest lift or with a bigger consequent set. Pairs can also be especially interesting





In [9]:



    


# Sort rules by confidence
confidenceSortedRules = rulesDataframe.sort_values(by = ["confidence", "support"], ascending=[False, False])
confidenceSortedRules.head(50)



    


















    
Out[9]:











  
    

      
      antecedants
      consequents
      support
      confidence
    

  
  
    

      100
      (QDeviceGfpRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer)
      62
      1.000000
    

    

      61
      (QDeviceGfpRbsPconsTer, QDeviceRbsPconsAmprTer)
      (QDeviceRbsPconsFlhdcTer)
      58
      1.000000
    

    

      79
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsAmprTer)
      (QDeviceRbsPconsFlhdcTer)
      58
      1.000000
    

    

      71
      (QDeviceAmprRbsPconsTer, QDeviceGfpRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer)
      56
      1.000000
    

    

      11
      (QDeviceAmprRbsPconsTer, QDeviceGfpRbsPconsTer...
      (QDeviceRbsPconsFlhdcTer)
      55
      1.000000
    

    

      50
      (QDeviceGfpRbsPconsTer, QGenotypePhenotype)
      (QDeviceRbsPconsFlhdcTer)
      54
      1.000000
    

    

      0
      (QDeviceRbsPconsAmprTer, QDeviceGfpRbsPconsTer...
      (QDeviceRbsPconsFlhdcTer)
      52
      1.000000
    

    

      24
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsAmprTe...
      (QDeviceRbsPconsFlhdcTer)
      52
      1.000000
    

    

      26
      (QDeviceAmprRbsPconsTer, QGenotypePhenotype)
      (QDeviceRbsPconsFlhdcTer, QDeviceRbsPconsAmprTer)
      52
      1.000000
    

    

      32
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsFlhdcT...
      (QDeviceRbsPconsAmprTer)
      52
      1.000000
    

    

      75
      (QDeviceAmprRbsPconsTer, QGenotypePhenotype)
      (QDeviceRbsPconsFlhdcTer)
      52
      1.000000
    

    

      92
      (QDeviceAmprRbsPconsTer, QGenotypePhenotype)
      (QDeviceRbsPconsAmprTer)
      52
      1.000000
    

    

      48
      (QDeviceRbsPconsAmprTer, QAmpicillin)
      (QDeviceRbsPconsFlhdcTer)
      51
      1.000000
    

    

      53
      (QDeviceGfpRbsPconsTer, QGreenFluorescence)
      (QDeviceRbsPconsFlhdcTer)
      51
      1.000000
    

    

      66
      (QDeviceGfpRbsPconsTer, QAmpicillin)
      (QDeviceRbsPconsFlhdcTer)
      50
      1.000000
    

    

      97
      (QDeviceRbsPconsAmprTer)
      (QDeviceRbsPconsFlhdcTer)
      65
      0.984848
    

    

      42
      (QDeviceRbsPconsAmprTer, QGenotypePhenotype)
      (QDeviceRbsPconsFlhdcTer)
      59
      0.983333
    

    

      82
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsFlhdcTer)
      (QDeviceRbsPconsAmprTer)
      58
      0.983051
    

    

      15
      (QDeviceAmprRbsPconsTer, QDeviceGfpRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer, QDeviceRbsPconsAmprTer)
      55
      0.982143
    

    

      20
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsFlhdcT...
      (QDeviceRbsPconsAmprTer)
      55
      0.982143
    

    

      86
      (QDeviceAmprRbsPconsTer, QDeviceGfpRbsPconsTer)
      (QDeviceRbsPconsAmprTer)
      55
      0.982143
    

    

      46
      (QGreenFluorescence, QDeviceRbsPconsAmprTer)
      (QDeviceRbsPconsFlhdcTer)
      50
      0.980392
    

    

      105
      (QDeviceAmprRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer)
      59
      0.967213
    

    

      1
      (QDeviceGfpRbsPconsTer, QGenotypePhenotype)
      (QDeviceRbsPconsFlhdcTer, QDeviceRbsPconsAmprTer)
      52
      0.962963
    

    

      9
      (QDeviceRbsPconsFlhdcTer, QDeviceGfpRbsPconsTe...
      (QDeviceRbsPconsAmprTer)
      52
      0.962963
    

    

      60
      (QDeviceGfpRbsPconsTer, QGenotypePhenotype)
      (QDeviceRbsPconsAmprTer)
      52
      0.962963
    

    

      81
      (QDeviceAmprRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer, QDeviceRbsPconsAmprTer)
      58
      0.950820
    

    

      110
      (QDeviceAmprRbsPconsTer)
      (QDeviceRbsPconsAmprTer)
      58
      0.950820
    

    

      74
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsFlhdcTer)
      (QDeviceGfpRbsPconsTer)
      56
      0.949153
    

    

      10
      (QDeviceRbsPconsFlhdcTer, QDeviceGfpRbsPconsTe...
      (QDeviceAmprRbsPconsTer)
      55
      0.948276
    

    

      12
      (QDeviceGfpRbsPconsTer, QDeviceRbsPconsAmprTer)
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsFlhdcTer)
      55
      0.948276
    

    

      13
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsAmprTer)
      (QDeviceRbsPconsFlhdcTer, QDeviceGfpRbsPconsTer)
      55
      0.948276
    

    

      18
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsFlhdcT...
      (QDeviceGfpRbsPconsTer)
      55
      0.948276
    

    

      83
      (QDeviceGfpRbsPconsTer, QDeviceRbsPconsAmprTer)
      (QDeviceAmprRbsPconsTer)
      55
      0.948276
    

    

      84
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsAmprTer)
      (QDeviceGfpRbsPconsTer)
      55
      0.948276
    

    

      63
      (QDeviceGfpRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer, QDeviceRbsPconsAmprTer)
      58
      0.935484
    

    

      65
      (QDeviceRbsPconsFlhdcTer, QDeviceGfpRbsPconsTer)
      (QDeviceRbsPconsAmprTer)
      58
      0.935484
    

    

      103
      (QDeviceGfpRbsPconsTer)
      (QDeviceRbsPconsAmprTer)
      58
      0.935484
    

    

      22
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsFlhdcTer)
      (QDeviceGfpRbsPconsTer, QDeviceRbsPconsAmprTer)
      55
      0.932203
    

    

      112
      (QBBFunctionTER)
      (QGenotypePhenotype)
      50
      0.925926
    

    

      73
      (QDeviceAmprRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer, QDeviceGfpRbsPconsTer)
      56
      0.918033
    

    

      107
      (QDeviceAmprRbsPconsTer)
      (QDeviceGfpRbsPconsTer)
      56
      0.918033
    

    

      98
      (QDeviceRbsPconsAmprTer)
      (QGenotypePhenotype)
      60
      0.909091
    

    

      96
      (QBioBricksDevicesComposition)
      (QGenotypePhenotype)
      69
      0.907895
    

    

      43
      (QDeviceRbsPconsFlhdcTer, QDeviceRbsPconsAmprTer)
      (QGenotypePhenotype)
      59
      0.907692
    

    

      70
      (QDeviceRbsPconsFlhdcTer, QDeviceGfpRbsPconsTer)
      (QDeviceAmprRbsPconsTer)
      56
      0.903226
    

    

      72
      (QDeviceGfpRbsPconsTer)
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsFlhdcTer)
      56
      0.903226
    

    

      106
      (QDeviceGfpRbsPconsTer)
      (QDeviceAmprRbsPconsTer)
      56
      0.903226
    

    

      17
      (QDeviceAmprRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer, QDeviceGfpRbsPconsTe...
      55
      0.901639
    

    

      88
      (QDeviceAmprRbsPconsTer)
      (QDeviceGfpRbsPconsTer, QDeviceRbsPconsAmprTer)
      55
      0.901639
    

  




















In [10]:



    


# Sort rules by size of consequent set
rulesDataframe["consequentSize"] = rulesDataframe["consequents"].apply(lambda x: len(x))
consequentSortedRules = rulesDataframe.sort_values(by = ["consequentSize", "confidence", "support"], ascending=[False, False, False])
consequentSortedRules.head(50)



    


















    
Out[10]:











  
    

      
      antecedants
      consequents
      support
      confidence
      consequentSize
    

  
  
    

      17
      (QDeviceAmprRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer, QDeviceGfpRbsPconsTe...
      55
      0.901639
      3
    

    

      16
      (QDeviceGfpRbsPconsTer)
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsFlhdcT...
      55
      0.887097
      3
    

    

      30
      (QDeviceAmprRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer, QDeviceRbsPconsAmprT...
      52
      0.852459
      3
    

    

      6
      (QDeviceGfpRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer, QDeviceRbsPconsAmprT...
      52
      0.838710
      3
    

    

      14
      (QDeviceRbsPconsAmprTer)
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsFlhdcT...
      55
      0.833333
      3
    

    

      26
      (QDeviceAmprRbsPconsTer, QGenotypePhenotype)
      (QDeviceRbsPconsFlhdcTer, QDeviceRbsPconsAmprTer)
      52
      1.000000
      2
    

    

      15
      (QDeviceAmprRbsPconsTer, QDeviceGfpRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer, QDeviceRbsPconsAmprTer)
      55
      0.982143
      2
    

    

      1
      (QDeviceGfpRbsPconsTer, QGenotypePhenotype)
      (QDeviceRbsPconsFlhdcTer, QDeviceRbsPconsAmprTer)
      52
      0.962963
      2
    

    

      81
      (QDeviceAmprRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer, QDeviceRbsPconsAmprTer)
      58
      0.950820
      2
    

    

      12
      (QDeviceGfpRbsPconsTer, QDeviceRbsPconsAmprTer)
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsFlhdcTer)
      55
      0.948276
      2
    

    

      13
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsAmprTer)
      (QDeviceRbsPconsFlhdcTer, QDeviceGfpRbsPconsTer)
      55
      0.948276
      2
    

    

      63
      (QDeviceGfpRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer, QDeviceRbsPconsAmprTer)
      58
      0.935484
      2
    

    

      22
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsFlhdcTer)
      (QDeviceGfpRbsPconsTer, QDeviceRbsPconsAmprTer)
      55
      0.932203
      2
    

    

      73
      (QDeviceAmprRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer, QDeviceGfpRbsPconsTer)
      56
      0.918033
      2
    

    

      72
      (QDeviceGfpRbsPconsTer)
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsFlhdcTer)
      56
      0.903226
      2
    

    

      88
      (QDeviceAmprRbsPconsTer)
      (QDeviceGfpRbsPconsTer, QDeviceRbsPconsAmprTer)
      55
      0.901639
      2
    

    

      5
      (QDeviceGfpRbsPconsTer, QDeviceRbsPconsAmprTer)
      (QDeviceRbsPconsFlhdcTer, QGenotypePhenotype)
      52
      0.896552
      2
    

    

      29
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsAmprTer)
      (QDeviceRbsPconsFlhdcTer, QGenotypePhenotype)
      52
      0.896552
      2
    

    

      44
      (QDeviceRbsPconsAmprTer)
      (QDeviceRbsPconsFlhdcTer, QGenotypePhenotype)
      59
      0.893939
      2
    

    

      21
      (QDeviceRbsPconsFlhdcTer, QDeviceGfpRbsPconsTer)
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsAmprTer)
      55
      0.887097
      2
    

    

      87
      (QDeviceGfpRbsPconsTer)
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsAmprTer)
      55
      0.887097
      2
    

    

      31
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsFlhdcTer)
      (QDeviceRbsPconsAmprTer, QGenotypePhenotype)
      52
      0.881356
      2
    

    

      62
      (QDeviceRbsPconsAmprTer)
      (QDeviceRbsPconsFlhdcTer, QDeviceGfpRbsPconsTer)
      58
      0.878788
      2
    

    

      80
      (QDeviceRbsPconsAmprTer)
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsFlhdcTer)
      58
      0.878788
      2
    

    

      52
      (QDeviceGfpRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer, QGenotypePhenotype)
      54
      0.870968
      2
    

    

      2
      (QGenotypePhenotype, QDeviceRbsPconsAmprTer)
      (QDeviceRbsPconsFlhdcTer, QDeviceGfpRbsPconsTer)
      52
      0.866667
      2
    

    

      25
      (QGenotypePhenotype, QDeviceRbsPconsAmprTer)
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsFlhdcTer)
      52
      0.866667
      2
    

    

      77
      (QDeviceAmprRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer, QGenotypePhenotype)
      52
      0.852459
      2
    

    

      91
      (QDeviceAmprRbsPconsTer)
      (QDeviceRbsPconsAmprTer, QGenotypePhenotype)
      52
      0.852459
      2
    

    

      19
      (QDeviceRbsPconsFlhdcTer, QDeviceRbsPconsAmprTer)
      (QDeviceAmprRbsPconsTer, QDeviceGfpRbsPconsTer)
      55
      0.846154
      2
    

    

      8
      (QDeviceRbsPconsFlhdcTer, QDeviceGfpRbsPconsTer)
      (QDeviceRbsPconsAmprTer, QGenotypePhenotype)
      52
      0.838710
      2
    

    

      59
      (QDeviceGfpRbsPconsTer)
      (QDeviceRbsPconsAmprTer, QGenotypePhenotype)
      52
      0.838710
      2
    

    

      85
      (QDeviceRbsPconsAmprTer)
      (QDeviceAmprRbsPconsTer, QDeviceGfpRbsPconsTer)
      55
      0.833333
      2
    

    

      56
      (QDeviceGfpRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer, QGreenFluorescence)
      51
      0.822581
      2
    

    

      67
      (QDeviceGfpRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer, QAmpicillin)
      50
      0.806452
      2
    

    

      7
      (QDeviceRbsPconsFlhdcTer, QDeviceRbsPconsAmprTer)
      (QDeviceGfpRbsPconsTer, QGenotypePhenotype)
      52
      0.800000
      2
    

    

      28
      (QDeviceRbsPconsFlhdcTer, QDeviceRbsPconsAmprTer)
      (QDeviceAmprRbsPconsTer, QGenotypePhenotype)
      52
      0.800000
      2
    

    

      100
      (QDeviceGfpRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer)
      62
      1.000000
      1
    

    

      61
      (QDeviceGfpRbsPconsTer, QDeviceRbsPconsAmprTer)
      (QDeviceRbsPconsFlhdcTer)
      58
      1.000000
      1
    

    

      79
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsAmprTer)
      (QDeviceRbsPconsFlhdcTer)
      58
      1.000000
      1
    

    

      71
      (QDeviceAmprRbsPconsTer, QDeviceGfpRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer)
      56
      1.000000
      1
    

    

      11
      (QDeviceAmprRbsPconsTer, QDeviceGfpRbsPconsTer...
      (QDeviceRbsPconsFlhdcTer)
      55
      1.000000
      1
    

    

      50
      (QDeviceGfpRbsPconsTer, QGenotypePhenotype)
      (QDeviceRbsPconsFlhdcTer)
      54
      1.000000
      1
    

    

      0
      (QDeviceRbsPconsAmprTer, QDeviceGfpRbsPconsTer...
      (QDeviceRbsPconsFlhdcTer)
      52
      1.000000
      1
    

    

      24
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsAmprTe...
      (QDeviceRbsPconsFlhdcTer)
      52
      1.000000
      1
    

    

      32
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsFlhdcT...
      (QDeviceRbsPconsAmprTer)
      52
      1.000000
      1
    

    

      75
      (QDeviceAmprRbsPconsTer, QGenotypePhenotype)
      (QDeviceRbsPconsFlhdcTer)
      52
      1.000000
      1
    

    

      92
      (QDeviceAmprRbsPconsTer, QGenotypePhenotype)
      (QDeviceRbsPconsAmprTer)
      52
      1.000000
      1
    

    

      48
      (QDeviceRbsPconsAmprTer, QAmpicillin)
      (QDeviceRbsPconsFlhdcTer)
      51
      1.000000
      1
    

    

      53
      (QDeviceGfpRbsPconsTer, QGreenFluorescence)
      (QDeviceRbsPconsFlhdcTer)
      51
      1.000000
      1
    

  




















In [11]:



    


# Select only pairs (rules with antecedent and consequent of size one)
# Sort pairs according to confidence
rulesDataframe["fusedRule"] = rulesDataframe[["antecedants", "consequents"]].apply(lambda x: frozenset().union(*x), axis=1)
rulesDataframe["ruleSize"] = rulesDataframe["fusedRule"].apply(lambda x: len(x))
pairRules = rulesDataframe.sort_values(by=["ruleSize", "confidence", "support"], ascending=[True, False, False])
pairRules.head(30)



    


















    
Out[11]:











  
    

      
      antecedants
      consequents
      support
      confidence
      consequentSize
      fusedRule
      ruleSize
    

  
  
    

      100
      (QDeviceGfpRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer)
      62
      1.000000
      1
      (QDeviceRbsPconsFlhdcTer, QDeviceGfpRbsPconsTer)
      2
    

    

      97
      (QDeviceRbsPconsAmprTer)
      (QDeviceRbsPconsFlhdcTer)
      65
      0.984848
      1
      (QDeviceRbsPconsFlhdcTer, QDeviceRbsPconsAmprTer)
      2
    

    

      105
      (QDeviceAmprRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer)
      59
      0.967213
      1
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsFlhdcTer)
      2
    

    

      110
      (QDeviceAmprRbsPconsTer)
      (QDeviceRbsPconsAmprTer)
      58
      0.950820
      1
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsAmprTer)
      2
    

    

      103
      (QDeviceGfpRbsPconsTer)
      (QDeviceRbsPconsAmprTer)
      58
      0.935484
      1
      (QDeviceGfpRbsPconsTer, QDeviceRbsPconsAmprTer)
      2
    

    

      112
      (QBBFunctionTER)
      (QGenotypePhenotype)
      50
      0.925926
      1
      (QBBFunctionTER, QGenotypePhenotype)
      2
    

    

      107
      (QDeviceAmprRbsPconsTer)
      (QDeviceGfpRbsPconsTer)
      56
      0.918033
      1
      (QDeviceAmprRbsPconsTer, QDeviceGfpRbsPconsTer)
      2
    

    

      98
      (QDeviceRbsPconsAmprTer)
      (QGenotypePhenotype)
      60
      0.909091
      1
      (QGenotypePhenotype, QDeviceRbsPconsAmprTer)
      2
    

    

      96
      (QBioBricksDevicesComposition)
      (QGenotypePhenotype)
      69
      0.907895
      1
      (QBioBricksDevicesComposition, QGenotypePhenot...
      2
    

    

      106
      (QDeviceGfpRbsPconsTer)
      (QDeviceAmprRbsPconsTer)
      56
      0.903226
      1
      (QDeviceAmprRbsPconsTer, QDeviceGfpRbsPconsTer)
      2
    

    

      102
      (QDeviceRbsPconsAmprTer)
      (QDeviceGfpRbsPconsTer)
      58
      0.878788
      1
      (QDeviceGfpRbsPconsTer, QDeviceRbsPconsAmprTer)
      2
    

    

      109
      (QDeviceRbsPconsAmprTer)
      (QDeviceAmprRbsPconsTer)
      58
      0.878788
      1
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsAmprTer)
      2
    

    

      99
      (QDeviceGfpRbsPconsTer)
      (QGenotypePhenotype)
      54
      0.870968
      1
      (QDeviceGfpRbsPconsTer, QGenotypePhenotype)
      2
    

    

      95
      (QUnequipDevice)
      (QGenotypePhenotype)
      66
      0.868421
      1
      (QUnequipDevice, QGenotypePhenotype)
      2
    

    

      94
      (QDeviceRbsPconsFlhdcTer)
      (QGenotypePhenotype)
      71
      0.865854
      1
      (QDeviceRbsPconsFlhdcTer, QGenotypePhenotype)
      2
    

    

      108
      (QDeviceAmprRbsPconsTer)
      (QGenotypePhenotype)
      52
      0.852459
      1
      (QDeviceAmprRbsPconsTer, QGenotypePhenotype)
      2
    

    

      111
      (QBBFunctionRBS)
      (QDeviceRbsPconsFlhdcTer)
      50
      0.847458
      1
      (QBBFunctionRBS, QDeviceRbsPconsFlhdcTer)
      2
    

    

      101
      (QDeviceGfpRbsPconsTer)
      (QGreenFluorescence)
      51
      0.822581
      1
      (QDeviceGfpRbsPconsTer, QGreenFluorescence)
      2
    

    

      93
      (QGreenFluorescence)
      (QGenotypePhenotype)
      69
      0.811765
      1
      (QGreenFluorescence, QGenotypePhenotype)
      2
    

    

      104
      (QDeviceGfpRbsPconsTer)
      (QAmpicillin)
      50
      0.806452
      1
      (QDeviceGfpRbsPconsTer, QAmpicillin)
      2
    

    

      61
      (QDeviceGfpRbsPconsTer, QDeviceRbsPconsAmprTer)
      (QDeviceRbsPconsFlhdcTer)
      58
      1.000000
      1
      (QDeviceRbsPconsFlhdcTer, QDeviceGfpRbsPconsTe...
      3
    

    

      79
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsAmprTer)
      (QDeviceRbsPconsFlhdcTer)
      58
      1.000000
      1
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsFlhdcT...
      3
    

    

      71
      (QDeviceAmprRbsPconsTer, QDeviceGfpRbsPconsTer)
      (QDeviceRbsPconsFlhdcTer)
      56
      1.000000
      1
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsFlhdcT...
      3
    

    

      50
      (QDeviceGfpRbsPconsTer, QGenotypePhenotype)
      (QDeviceRbsPconsFlhdcTer)
      54
      1.000000
      1
      (QDeviceRbsPconsFlhdcTer, QDeviceGfpRbsPconsTe...
      3
    

    

      75
      (QDeviceAmprRbsPconsTer, QGenotypePhenotype)
      (QDeviceRbsPconsFlhdcTer)
      52
      1.000000
      1
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsFlhdcT...
      3
    

    

      92
      (QDeviceAmprRbsPconsTer, QGenotypePhenotype)
      (QDeviceRbsPconsAmprTer)
      52
      1.000000
      1
      (QDeviceAmprRbsPconsTer, QDeviceRbsPconsAmprTe...
      3
    

    

      48
      (QDeviceRbsPconsAmprTer, QAmpicillin)
      (QDeviceRbsPconsFlhdcTer)
      51
      1.000000
      1
      (QDeviceRbsPconsFlhdcTer, QDeviceRbsPconsAmprT...
      3
    

    

      53
      (QDeviceGfpRbsPconsTer, QGreenFluorescence)
      (QDeviceRbsPconsFlhdcTer)
      51
      1.000000
      1
      (QDeviceRbsPconsFlhdcTer, QDeviceGfpRbsPconsTe...
      3
    

    

      66
      (QDeviceGfpRbsPconsTer, QAmpicillin)
      (QDeviceRbsPconsFlhdcTer)
      50
      1.000000
      1
      (QDeviceRbsPconsFlhdcTer, QDeviceGfpRbsPconsTe...
      3
    

    

      42
      (QDeviceRbsPconsAmprTer, QGenotypePhenotype)
      (QDeviceRbsPconsFlhdcTer)
      59
      0.983333
      1
      (QDeviceRbsPconsFlhdcTer, QDeviceRbsPconsAmprT...
      3
    

  




















In [12]:



    


correctedScientific.columns



    


















    
Out[12]:








Index(['QGenotypePhenotype', 'QBioBricksDevicesComposition', 'QAmpicillin',
       'QBBNamePlasmid', 'QBBFunctionTER', 'QBBNamePromoter',
       'QBBFunctionGameCDS', 'QBBNameTerminator', 'QBBFunctionBiologyCDS',
       'QBBNameRBS', 'QBBExampleCDS', 'QBBNameCDS', 'QBBFunctionPR',
       'QBBFunctionRBS', 'QBBFunctionPlasmid', 'QBBNameOperator',
       'QDeviceRbsPconsFlhdcTer', 'QDevicePconsRbsFlhdcTer',
       'QDevicePbadRbsGfpTer', 'QDevicePbadGfpRbsTer', 'QDeviceGfpRbsPconsTer',
       'QDevicePconsGfpRbsTer', 'QDeviceAmprRbsPconsTer',
       'QDeviceRbsPconsAmprTer', 'QGreenFluorescence', 'QUnequipDevice',
       'QDevicePbadRbsAraTer'],
      dtype='object')

















In [13]:



    


# Sort questions by number of apparition in consequents
for q in scientificQuestions:
    rulesDataframe[q+"c"] = rulesDataframe["consequents"].apply(lambda x: 1 if q in x else 0)
occurenceInConsequents = rulesDataframe.loc[:,scientificQuestions[0]+"c":scientificQuestions[-1]+"c"].sum(axis=0)

occurenceInConsequents.sort_values(inplace=True, ascending=False)
occurenceInConsequents



    


















    
Out[13]:








QDeviceRbsPconsFlhdcTerc         43
QGenotypePhenotypec              33
QDeviceRbsPconsAmprTerc          30
QDeviceGfpRbsPconsTerc           21
QDeviceAmprRbsPconsTerc          19
QGreenFluorescencec               5
QAmpicillinc                      4
QBBExampleCDSc                    0
QBioBricksDevicesCompositionc     0
QBBNamePlasmidc                   0
QBBFunctionTERc                   0
QBBNamePromoterc                  0
QBBFunctionGameCDSc               0
QBBNameTerminatorc                0
QBBFunctionBiologyCDSc            0
QBBNameRBSc                       0
QDevicePbadRbsAraTerc             0
QBBNameCDSc                       0
QBBFunctionPRc                    0
QUnequipDevicec                   0
QBBFunctionPlasmidc               0
QBBNameOperatorc                  0
QDevicePconsRbsFlhdcTerc          0
QDevicePbadRbsGfpTerc             0
QDevicePbadGfpRbsTerc             0
QDevicePconsGfpRbsTerc            0
QBBFunctionRBSc                   0
dtype: int64

















In [14]:



    


# Sort questions by number of apparition in antecedants
for q in scientificQuestions:
    rulesDataframe[q+"a"] = rulesDataframe["antecedants"].apply(lambda x: 1 if q in x else 0)
occurenceInAntecedants = rulesDataframe.loc[:,scientificQuestions[0]+"a":scientificQuestions[-1]+"a"].sum(axis=0)
occurenceInAntecedants.sort_values(inplace=True, ascending=False)
occurenceInAntecedants



    


















    
Out[14]:








QDeviceRbsPconsAmprTera          41
QDeviceGfpRbsPconsTera           41
QDeviceRbsPconsFlhdcTera         37
QDeviceAmprRbsPconsTera          33
QGenotypePhenotypea              19
QGreenFluorescencea              10
QAmpicillina                      9
QUnequipDevicea                   4
QBioBricksDevicesCompositiona     1
QBBFunctionTERa                   1
QBBFunctionRBSa                   1
QBBNameOperatora                  0
QBBFunctionPlasmida               0
QDevicePconsRbsFlhdcTera          0
QBBFunctionPRa                    0
QBBNameCDSa                       0
QBBExampleCDSa                    0
QBBNameRBSa                       0
QBBFunctionBiologyCDSa            0
QBBNameTerminatora                0
QBBFunctionGameCDSa               0
QBBNamePromotera                  0
QDevicePbadRbsGfpTera             0
QBBNamePlasmida                   0
QDevicePbadGfpRbsTera             0
QDevicePconsGfpRbsTera            0
QDevicePbadRbsAraTera             0
dtype: int64

















In [15]:



    


sortedPrePostProgression = pd.read_csv("../../data/sortedPrePostProgression.csv")
sortedPrePostProgression.index = sortedPrePostProgression.iloc[:,0]
sortedPrePostProgression = sortedPrePostProgression.drop(sortedPrePostProgression.columns[0], axis = 1)
del sortedPrePostProgression.index.name
sortedPrePostProgression.loc['occ_ant',:] = 0
sortedPrePostProgression.loc['occ_csq',:] = 0
sortedPrePostProgression



    


















    
Out[15]:











  
    

      
      Name: Operator XXX
      Device: PBAD:RBS:ARA:TER
      Name: RBS
      Name: CDS
      Device: PBAD:RBS:GFP:TER
      Function - game: CDS
      Function - biology: CDS
      Name: PR
      Function: PR
      Device: PCONS:GFP:RBS:TER XXX
      ...
      Interested in video games
      Interested in biology
      Studied biology
      Play video games
      Heard about Synthetic biology or BioBricks
      Volunteered to answer more questions
      Language
      Enjoyed playing
      Played Hero.Coli
      Temporality
    

  
  
    

      pretest
      0.0
      4.0
      0.0
      6.0
      2.0
      1.0
      3.0
      4.0
      0.0
      2.0
      ...
      77.0
      74.0
      6.0
      74.0
      0.0
      100.0
      6.0
      6.0
      0.0
      0.0
    

    

      posttest
      4.0
      15.0
      13.0
      21.0
      20.0
      18.0
      22.0
      25.0
      21.0
      32.0
      ...
      77.0
      74.0
      6.0
      74.0
      0.0
      100.0
      6.0
      80.0
      100.0
      100.0
    

    

      progression
      4.0
      11.0
      13.0
      14.0
      17.0
      17.0
      18.0
      21.0
      21.0
      30.0
      ...
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      73.0
      100.0
      100.0
    

    

      occ_ant
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      ...
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
    

    

      occ_csq
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      ...
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
    

  



5 rows × 43 columns



















In [16]:



    


for questionA, occsA in enumerate(occurenceInAntecedants):
    questionVariableName = occurenceInAntecedants.index[questionA][:-1]
    question = globals()[questionVariableName]
    questionC = questionVariableName + "c"
    sortedPrePostProgression.loc['occ_ant',question] = occsA
    occsC = occurenceInConsequents.loc[questionC]
    sortedPrePostProgression.loc['occ_csq',question] = occsC
    #print(questionVariableName+"='"+question+"'")
    #print("\t"+questionVariableName+"a="+str(occsA)+","+questionC+"="+str(occsC))
    #print()
sortedPrePostProgression.T



    


















    
Out[16]:











  
    

      
      pretest
      posttest
      progression
      occ_ant
      occ_csq
    

  
  
    

      Name: Operator XXX
      0.0
      4.0
      4.0
      0.0
      0.0
    

    

      Device: PBAD:RBS:ARA:TER
      4.0
      15.0
      11.0
      0.0
      0.0
    

    

      Name: RBS
      0.0
      13.0
      13.0
      0.0
      0.0
    

    

      Name: CDS
      6.0
      21.0
      14.0
      0.0
      0.0
    

    

      Device: PBAD:RBS:GFP:TER
      2.0
      20.0
      17.0
      0.0
      0.0
    

    

      Function - game: CDS
      1.0
      18.0
      17.0
      0.0
      0.0
    

    

      Function - biology: CDS
      3.0
      22.0
      18.0
      0.0
      0.0
    

    

      Name: PR
      4.0
      25.0
      21.0
      0.0
      0.0
    

    

      Function: PR
      0.0
      21.0
      21.0
      0.0
      0.0
    

    

      Device: PCONS:GFP:RBS:TER XXX
      2.0
      32.0
      30.0
      0.0
      0.0
    

    

      Example: CDS
      0.0
      30.0
      30.0
      0.0
      0.0
    

    

      Name: Plasmid
      1.0
      37.0
      36.0
      0.0
      0.0
    

    

      Device: PBAD:GFP:RBS:TER XXX
      0.0
      37.0
      37.0
      0.0
      0.0
    

    

      Device: PCONS:RBS:FLHDC:TER
      0.0
      37.0
      37.0
      0.0
      0.0
    

    

      Function: RBS
      7.0
      50.0
      42.0
      1.0
      0.0
    

    

      Name: TER
      11.0
      53.0
      42.0
      0.0
      0.0
    

    

      Ampicillin antibiotic
      26.0
      70.0
      43.0
      9.0
      4.0
    

    

      Function: Plasmid
      0.0
      44.0
      44.0
      0.0
      0.0
    

    

      Function: TER
      2.0
      47.0
      45.0
      1.0
      0.0
    

    

      BioBricks and devices composition
      10.0
      61.0
      51.0
      1.0
      0.0
    

    

      Unequip the movement device: effect
      8.0
      61.0
      52.0
      4.0
      0.0
    

    

      Device: AMPR:RBS:PCONS:TER XXX
      2.0
      54.0
      52.0
      33.0
      19.0
    

    

      Genotype and phenotype
      28.0
      82.0
      53.0
      19.0
      33.0
    

    

      Device: GFP:RBS:PCONS:TER XXX
      0.0
      56.0
      56.0
      41.0
      21.0
    

    

      Green fluorescence
      7.0
      65.0
      57.0
      10.0
      5.0
    

    

      Device: RBS:PCONS:AMPR:TER XXX
      0.0
      62.0
      62.0
      41.0
      30.0
    

    

      Device: RBS:PCONS:FLHDC:TER XXX
      4.0
      70.0
      65.0
      37.0
      43.0
    

    

      Want to learn more about Engineering
      85.0
      76.0
      -8.0
      0.0
      0.0
    

    

      Want to learn more about Synthetic biology
      80.0
      76.0
      -3.0
      0.0
      0.0
    

    

      Want to learn more about Video games
      84.0
      81.0
      -3.0
      0.0
      0.0
    

    

      Want to learn more about Biology
      85.0
      83.0
      -2.0
      0.0
      0.0
    

    

      Age
      32.0
      32.0
      0.0
      0.0
      0.0
    

    

      Gender
      26.0
      26.0
      0.0
      0.0
      0.0
    

    

      Interested in video games
      77.0
      77.0
      0.0
      0.0
      0.0
    

    

      Interested in biology
      74.0
      74.0
      0.0
      0.0
      0.0
    

    

      Studied biology
      6.0
      6.0
      0.0
      0.0
      0.0
    

    

      Play video games
      74.0
      74.0
      0.0
      0.0
      0.0
    

    

      Heard about Synthetic biology or BioBricks
      0.0
      0.0
      0.0
      0.0
      0.0
    

    

      Volunteered to answer more questions
      100.0
      100.0
      0.0
      0.0
      0.0
    

    

      Language
      6.0
      6.0
      0.0
      0.0
      0.0
    

    

      Enjoyed playing
      6.0
      80.0
      73.0
      0.0
      0.0
    

    

      Played Hero.Coli
      0.0
      100.0
      100.0
      0.0
      0.0
    

    

      Temporality
      0.0
      100.0
      100.0
      0.0
      0.0
    

  




















In [ ]:

Content source: CyberCRI/dataanalysis-herocoli-redmetrics

Similar notebooks:

notebook.community | gallery | about