I have a dataset X which I have tried to convert into a dataframe.
The dataset X is as follows:
X= woe_transform.fit_transform(df)
libelle_situation_professionnelle:AUTRES libelle_situation_professionnelle:RETRAITE ... montant_echeance_d:(1347.0, 1561.0] montant_echeance_d:(1709.0, 15508500.0]
0 0 0 ... False False
[1 rows x 26 columns]
Iam trying to convert it to a dataframe ( i managed to do for one column only).
feature_name = X.columns.values
feature_values=X.iloc[0].values
summary_table = pd.DataFrame(columns=["Feature name"], data=feature_name)
print(summary_table)
Feature name
0 libelle_situation_professionnelle:AUTRES
1 libelle_situation_professionnelle:RETRAITE
2 libelle_situation_professionnelle:SALARIE
3 libelle_situation_professionnelle:TRAVAILLEUR ...
4 solde_trim1_d:(-6691655.0, 436.0]
5 solde_trim1_d:(436.0, 3895.0]
6 solde_trim1_d:(3895.0, 33317.0]
7 duree_dossier_d:(120, 180]
8 duree_dossier_d:(180, 240]
9 duree_dossier_d:(240, 400]
10 montant_nominal_d:(0, 140000]
11 montant_nominal_d:(170500, 180500]
12 montant_nominal_d:(180500, 205000]
13 montant_nominal_d:(205000, 220000]
14 montant_nominal_d:(220000, 412000]
15 montant_nominal_d:(412000, 10000000000000]
16 taux_interets_d:(0.0, 4.2]
17 taux_interets_d:(5.5, 6.4]
18 taux_interets_d:(6.4, 8.0]
19 mois_anciennete_d:(6, 12]
20 mois_anciennete_d:(12, 24]
21 mois_anciennete_d:(24, 48]
22 mois_anciennete_d:(48, 500]
23 montant_echeance_d:(0.0, 1347.0]
24 montant_echeance_d:(1347.0, 1561.0]
25 montant_echeance_d:(1709.0, 15508500.0]
I am looking to do it for both columns feature_values and feature_name in order to have a dataframe with two columns as opposed to one.
I have tried this code but it failed.
summary_table = pd.DataFrame(columns=["Feature name", 'Feature Values'], data=[feature_name, features_values])
Can someone help please?
The 'data' parameter expects a list of rows or a dictionary, not a list of columns.
Try :
symmary_table = pd.DataFrame({
"Feature name": X.columns.values,
"Feature Values": X.iloc[0].values
})