Notebook Séance 2

UE8: Introduction à l’analyse de données

print("Bonjour")

Bonjour

sous_total = 5 + 3 * 12
sous_total

41

Un morceau de code pour illustrer l’usage des variables

prix_bombon = 0.10
prix_croissant = 1.0
prix_pain = 1.2
total = prix_bombon * 8
total = total + prix_croissant * 5
total = total + prix_pain * 2
print("Je dois "+str(total)+" euros")

Je dois 8.2 euros

import pandas

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

rt = df['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

subjects = df['Subject']
subjects.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

rt.min()

2703

df.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

qs = [ (q+1)/10 for q in range(9) ]
print(qs)
rt.quantile(qs)

[0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]





0.1     6223.0
0.2     7427.2
0.3     8370.9
0.4     9315.0
0.5    10262.5
0.6    11304.6
0.7    12761.3
0.8    15054.2
0.9    19872.0
Name: RT, dtype: float64

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

filtre = (rt < 11000)
df[filtre]

df[(df['RT'] < 11000)]

df

df[(df['Name_A'] == 0) & (df['RT'] > 14000)]

df[(df['Name_A'] == 0) & (df['RT'] > 14000)]['RT'].mean()

21400.008333333335