Analizamos las obras maestras de la pintura con la ayuda de ML clásico.

#      
def load_image_by_index(i):
    image_path = paintings_links.iloc[i].img_path
    img = cv2.imdecode(np.fromfile(str(Path.cwd()/image_path), np.uint8), cv2.IMREAD_UNCHANGED)
    return img    
#    
def get_hist_data_by_index(img_index):
    bin_div = 5 
    img = load_image_by_index(img_index)
    b, bins=  np.histogram(img[:,:,0], bins=255//bin_div, range=(0,255), density=True)
    g = np.histogram(img[:,:,1], bins=255//bin_div, range=(0,255), density=True)[0]
    r = np.histogram(img[:,:,2], bins=255//bin_div, range=(0,255), density=True)[0]
    return bins, r, g, b
#       
def plot_image_with_hist_by_index(img_index, height=6):
    bins, r, g, b = get_hist_data_by_index(img_index)
    img = load_image_by_index(img_index)
    fig = plt.figure(constrained_layout=True)

    if img.shape[0] < img.shape[1]:
        width_ratios = [3,1]
    else:
        width_ratios = [1,1]
        
    gs = GridSpec(3, 2, figure=fig, 
                  width_ratios = [3,1]
                 )
    ax_img = fig.add_subplot(gs[:,0])

    ax_r = fig.add_subplot(gs[0, 1])
    ax_g = fig.add_subplot(gs[1, 1], sharey=ax_r)
    ax_b = fig.add_subplot(gs[2, 1], sharey=ax_r)

    ax_img.imshow(cv2.cvtColor(img, cv2.COLOR_BGR2RGB),aspect = 'equal')
    ax_img.axis('off')
    
    ax_r.bar(bins[:-1], r, width = 5, color='red',alpha=0.7)
    ax_g.bar(bins[:-1], g, width = 5, color='green',alpha=0.7)
    ax_b.bar(bins[:-1], b, width = 5, color='blue',alpha=0.7)

    ax_r.axes.get_xaxis().set_ticks([])
    ax_r.axes.get_yaxis().set_ticks([])
    ax_g.axes.get_xaxis().set_ticks([])
    ax_g.axes.get_yaxis().set_ticks([])
    ax_b.axes.get_xaxis().set_ticks([])
    ax_b.axes.get_yaxis().set_ticks([])
    fig.suptitle("{} - {}".format(paintings_links.iloc[img_index].artist_name, 
                                 paintings_links.iloc[img_index].picture_name),ha= "left")
    
    fig.set_figheight(height)
    plt.axis('tight')
    if img.shape[0] < img.shape[1]:
        fig.set_figwidth(img.shape[1] *height / img.shape[0] *1.25)
    else:
        fig.set_figwidth(img.shape[1] *height / img.shape[0] *1.5)
    plt.show()

#       ,       
res = []
error = []
for img_index in tqdm(range(paintings_links.shape[0])):
    try:
        bins, r, g, b = get_hist_data_by_index(img_index)
        res.append(np.hstack([r,g,b]))
    except:
        res.append(np.zeros(153,))
        error.append(img_index)
        
np_res = np.vstack(res)
#    
pd.DataFrame(np_res).to_pickle("histograms.pkl")
histograms = pd.read_pickle("histograms.pkl")
#  .         .   10    
one_class_svm = OneClassSVM(nu=10 / histograms.shape[0], gamma='auto')
one_class_svm.fit(histograms[~histograms.index.isin(bad_images)])
#  
svm_outliers = one_class_svm.predict(histograms)
svm_outliers = np.array([1 if label == -1 else 0 for label in svm_outliers])
#   
uncommon_images = paintings_links[(svm_outliers ==1) & (~histograms.index.isin(bad_images))].index.values
for i in uncommon_images:
    plot_image_with_hist_by_index(i,4)

#  ,        
from scipy import spatial
def find_closest(target_id,n=5):
    distance_vector = np.apply_along_axis(spatial.distance.cosine,
                        arr=histograms,
                       axis=1,
                       v=histograms.values[target_id])
    return np.argsort(distance_vector)[:n]

# ,        
def get_hist_data_by_index_and_colorspace(bgr_img, colorspace):
    bin_div = 5
    img_cvt = cv2.cvtColor(bgr_img, getattr(cv2, colorspace))
    c1, bins =  np.histogram(img_cvt[:,:,0], bins=255//bin_div, range=(0,255), density=True)
    c2 = np.histogram(img_cvt[:,:,1], bins=255//bin_div, range=(0,255), density=True)[0]
    c3 = np.histogram(img_cvt[:,:,2], bins=255//bin_div, range=(0,255), density=True)[0]
    return bins, c1, c2, c3
#        
all_res = {}
all_errors = {}
for colorspace in list_of_color_spaces:
    all_res[colorspace] =[]
    all_errors[colorspace] =[]
for img_index in tqdm(range(paintings_links.shape[0]) ):
    
    for colorspace in list_of_color_spaces:
        try:
            bgr_img = load_image_by_index(img_index)
            bins, c1, c2, c3 = get_hist_data_by_index_and_colorspace(bgr_img, colorspace)
            all_res[colorspace].append(np.hstack([c1, c2, c3]))
        except:
            all_res[colorspace].append(np.zeros(153,))
            all_errors[colorspace].append(img_index)
all_res_np = {}
for colorspace in list_of_color_spaces:  
    all_res_np[colorspace] = np.vstack(all_res[colorspace])
res = []
#        
for colorspace in tqdm(list_of_color_spaces):
    temp_df = pd.DataFrame(all_res_np.get(colorspace))
    temp_x_train =   temp_df[temp_df.index.isin(X_train.index.values)]
    temp_x_test =   temp_df[temp_df.index.isin(X_test.index.values)]

    xgb=XGBClassifier()
    xgb.fit(temp_x_train, y_train)
    current_res = classification_report(y_test, xgb.predict(temp_x_test), labels=None, target_names=None, output_dict=True).get("macro avg")
    current_res["colorspace"] = colorspace
    res.append(current_res)
pd.DataFrame(res).sort_values(by="f1-score")

#          
def plot_composition_analysis(image_index):
    img = load_image_by_index(image_index)
    luv_img = cv2.cvtColor(load_image_by_index(image_index), cv2.COLOR_BGR2LUV)
    closest_colors = np.argmin(euclidean_distances(luv_img.reshape(-1,3),wheel_colors_luv),axis=1)
    wheel_colors2[closest_colors].reshape(luv_img.shape)
    color_areas_img = wheel_colors2[closest_colors].reshape(img.shape)

    v, c = get_image_colors(image_index)
    #         
    c_int = (c*img.shape[1]).astype(int)
    c_int_delta = img.shape[1] - sum(c_int)
    c_int[np.argmax(c_int)] = c_int[np.argmax(c_int)] + c_int_delta

    _ = []

    for i, vi in enumerate(v):
        bar_width = c_int[i]
        _.append(np.tile(wheel_colors2[vi], (150,bar_width,1)))
    color_bar_img = np.hstack(_)
    final_image = np.hstack([
                                np.vstack([img,
                                           np.tile(np.array([254,254,254]),(160,img.shape[1],1))]),

                                np.tile(np.array([254,254,254]),(img.shape[0]+160,10,1)),
                                np.vstack([color_areas_img,
                                           np.tile(np.array([254,254,254]),(10,img.shape[1],1)),
                                           color_bar_img])
                            ])
    h = 12
    w = h / final_image.shape[1] * final_image.shape[0]
    fig = plt.figure(figsize=(h,w))
    plt.imshow(cv2.cvtColor(final_image.astype(np.uint8), cv2.COLOR_BGR2RGB),interpolation='nearest', aspect='auto')
    plt.title("{} - {}".format(paintings_links.iloc[image_index].artist_name, 
                             paintings_links.iloc[image_index].picture_name),ha= "center")
    plt.axis('off');