plot color by author but cluster by kmeans/tf-idf python

Question

Hej!

my first time working with k-means/tf-idf/document cluster. I cluster text files with k-means/tf-idf which works great. I plot (PCA) and can see the clusters nicely.

But now I want the authors from the texts as color indicator, not the cluster/topic. Does anyone know how to do it?

file_list = glob.glob(os.path.join(os.getcwd(), "myFiles", "*.txt"))

dataset = []

for file_path in file_list:
    with open(file_path) as f_input:
        dataset.append(f_input.read())

vectorizer = TfidfVectorizer(stop_words='english')


vectorized_documents = vectorizer.fit_transform(dataset) 
  
pca = PCA(n_components=2) 
reduced_data = pca.fit_transform(vectorized_documents.toarray()) 
  
num_clusters = 7
kmeans = KMeans(n_clusters=num_clusters, n_init=5, 
                max_iter=500, random_state=42) 
kmeans.fit(vectorized_documents) 
  

# create a dataframe to store the results 
results = pd.DataFrame() 
results['document'] = dataset 
results['cluster'] = kmeans.labels_ 


# plot the results 
colors = ['black', 'red', 'green', 'yellow', 'blue', 'orange', 'purple'] 
cluster = ['0', '1','2', '3', '4', '5', '6'] 
for i in range(num_clusters): 
    plt.scatter(reduced_data[kmeans.labels_ == i, 0], 
                reduced_data[kmeans.labels_ == i, 1],  
                s=10, color=colors[i],  
                label=f' {cluster[i]}') 
plt.legend() 
plt.show()