UE8: Notebook de la séance 2

# Pour utiliser les bibliothèques
import pandas

Chargement des données du fichier Donnees_M2_RD.xlsx

dfxls = pandas.read_excel("Donnees_M2_RD.xlsx")

Chargement des dataframes expérimentaux du M1 dans un tableau

expes = []
for i in range(8):
    filename = "expe/subject-"+str(i)+".csv"
    print("Loading "+filename)
    df = pandas.read_csv(filename)
    df['Subject'] = i
    expes.append(df)
dfm1 = pandas.concat(expes)

Loading expe/subject-0.csv
Loading expe/subject-1.csv
Loading expe/subject-2.csv
Loading expe/subject-3.csv
Loading expe/subject-4.csv
Loading expe/subject-5.csv
Loading expe/subject-6.csv
Loading expe/subject-7.csv

dfxls

dfm1

for col in df.axes[1]:
    print(col)

acc
accuracy
average_response_time
avg_rt
background
canvas_backend
clock_backend
color_backend
correct
correct_message_debut_tirage
correct_reponse_question1
correct_reponse_question2
correct_welcome
count_boucle_images
count_choix_csv
count_choix_csv2
count_config_script
count_experiment
count_getting_started
count_image
count_image_et_questions
count_message_debut_tirage
count_question1
count_question1_feedback
count_question2
count_question2_feedback
count_reponse_question1
count_reponse_question2
count_resultats_logger
count_tirage
count_tirage_loop
count_welcome
datetime
description
disable_garbage_collection
experiment_file
experiment_path
fichier_csv
font_bold
font_family
font_italic
font_size
font_underline
foreground
form_clicks
fullscreen
height
image
keyboard_backend
live_row
live_row_boucle_images
live_row_tirage_loop
logfile
mouse_backend
nombre_tirages
num_tirage
opensesame_codename
opensesame_version
q1
q2
rep_autorisee1
rep_autorisee2
rep_ok1
rep_ok2
repeat_cycle
response
response_message_debut_tirage
response_reponse_question1
response_reponse_question2
response_time
response_time_message_debut_tirage
response_time_reponse_question1
response_time_reponse_question2
response_time_welcome
response_welcome
round_decimals
sampler_backend
sound_buf_size
sound_channels
sound_freq
sound_sample_size
start
subject_nr
subject_parity
time_boucle_images
time_choix_csv
time_choix_csv2
time_config_script
time_experiment
time_getting_started
time_image
time_image_et_questions
time_message_debut_tirage
time_question1
time_question1_feedback
time_question2
time_question2_feedback
time_reponse_question1
time_reponse_question2
time_resultats_logger
time_tirage
time_tirage_loop
time_welcome
tirage
title
total_correct
total_response_time
total_responses
width
Subject

dfxls["Subject"].drop_duplicates()

0       P_ADI_331
400     P_ALM_345
800     P_AMY_346
1200    P_BAM_347
1600    P_BEH_340
2000    P_BLC_325
2399    P_BLR_321
2798    P_BOA_321
3197    P_BOC_342
3597    P_CAR_327
3995    P_CAV_333
4395    P_CON_336
4795    P_GAM_338
5195    P_GHM_334
5595    P_GRC_341
5995    P_GRF_322
6394    P_LAC_354
6794    P_LEG_335
7194    P_MOE_339
7594    P_ROS_336
7994    P_SOA_337
8394    P_TAI_343
8794    P_VAL_329
9194    P_VAR_330
Name: Subject, dtype: object

dfxls

rt = dfxls["RT"]
rt

0       18865
1       13157
2       11628
3       10068
4       11801
        ...  
9589     7626
9590     6349
9591     9031
9592    16323
9593    10139
Name: RT, Length: 9594, dtype: int64

rt.max()

103152

rt.mean()

12050.088597039816

rt.std()

7085.96882950782

rt.quantile(0.4)

9315.000000000002

dfxls.min()

Subject     P_ADI_331
Name_A              0
Name_B              0
Dist_A              1
Dist_B              1
Mode              Dic
Space               E
Side                D
Response            1
RT               2703
dtype: object

rt.quantile([0.25,0.5,0.75])

0.25     7896.25
0.50    10262.50
0.75    13696.50
Name: RT, dtype: float64

condition = (rt >= 12000)
condition

0        True
1        True
2       False
3       False
4       False
        ...  
9589    False
9590    False
9591    False
9592     True
9593    False
Name: RT, Length: 9594, dtype: bool

rt

0       18865
1       13157
2       11628
3       10068
4       11801
        ...  
9589     7626
9590     6349
9591     9031
9592    16323
9593    10139
Name: RT, Length: 9594, dtype: int64

dfxls

Ici condition est une série de booléens

dfxls[condition]

rt = dfxls["RT"]
cond = rt >= 12000
dfxls[cond]

dfxls[dfxls["RT"] >= 12000]

dfxls["RT" >= 12000]

---------------------------------------------------------------------------

TypeError                                 Traceback (most recent call last)

Cell In[30], line 1
----> 1 dfxls["RT" >= 12000]


TypeError: '>=' not supported between instances of 'str' and 'int'

# on se rappelle que rt contient dfxls["RT"]
dfxls[rt >= 12000]

sup_8000 = (rt >= 8000)
inf_12000 = (rt <= 12000)

sup_8000

0        True
1        True
2        True
3        True
4        True
        ...  
9589    False
9590    False
9591     True
9592     True
9593     True
Name: RT, Length: 9594, dtype: bool

inf_12000

0       False
1       False
2        True
3        True
4        True
        ...  
9589     True
9590     True
9591     True
9592    False
9593     True
Name: RT, Length: 9594, dtype: bool

entre_8000_12000 = (sup_8000 & inf_12000)
entre_8000_12000

0       False
1       False
2        True
3        True
4        True
        ...  
9589    False
9590    False
9591     True
9592    False
9593     True
Name: RT, Length: 9594, dtype: bool

dfxls[entre_8000_12000]

dfxls[(dfxls["RT"] >= 8000) & (dfxls["RT"] <= 12000)]

rt = dfxls["RT"]
df_8_12 = dfxls[(rt >= 8000) & (rt <= 12000)]
df_8_12["Name_A"]

2       4
3       2
4       1
9       2
11      1
       ..
9576    1
9578    2
9581    3
9591    2
9593    0
Name: Name_A, Length: 3761, dtype: int64

dfxls[dfxls["RT"] >= 80000]["Subject"].drop_duplicates()

2798    P_BOA_321
3299    P_BOC_342
6447    P_LAC_354
9091    P_VAL_329
9425    P_VAR_330
Name: Subject, dtype: object