ValueError: n_components=4 must be between 0 and min(n_samples, n_features)=2 with svd_solver='full'

Question

I get an error with my code like this

for n, df_process in enumerate(all_df):
                #Normalisasi data dengan metode Standard Scaler
                scaler=StandardScaler()
                scaler.fit(df_process)
                scaled_data=scaler.transform(df_process)
                #Menentukan jumlah komponen dalam PCA
                if n == 0:
                    pca=PCA(n_components=total_faktor_positif, svd_solver='full')
                else:
                    pca=PCA(n_components=total_faktor_negatif, svd_solver='full')

                #Fitting PCA dari data yang sudah normalisasi
                pca.fit(scaled_data)
                #Dicari PCA dari data yang sudah normalisasi
                x_pca=pca.transform(scaled_data)
                factor = []
                for pc in x_pca:
                    factor.append(np.argmax(pc))
                all_factor.append(factor)
                print (all_factor)
                all_pca.append(x_pca)

Clustering dari hasil PCA yang sudah didapatkan

how can I fix them? please help:( because today is my essay

Answer 1

The n_components of PCA must be lower than min(n_samples, n_features).

In this case, min(n_samples, n_features)=2, so n_components only accept value between [0,2], but you give it 4.

You can try with: n_components=2