simPlot.py 文件源码

def tSNE_model(Vt,aid_dict):
    tsne_model = TSNE(n_components=2, verbose=1, random_state=0)
    tsne_V = tsne_model.fit_transform(np.transpose(Vt))
    # Put data in a pandas dataframe:
    tsne_df = pd.DataFrame(tsne_V, columns=['x', 'y'])
    # Save it:
    tsne_df.to_csv('results\\tsne_svd.csv')
    # Get anime names:
    con = sqlite3.connect('user_anime_data.db')
    cur = con.cursor()
    anime_data = cur.execute('SELECT Anime, Name, Score FROM animeData').fetchall()
    anime_data=dict([(x[0],(x[1],x[2])) for x in anime_data])
    anime_names = [anime_data[aid_dict[x]][0] for x in range(Vt.shape[1])]
    anime_scores = [anime_data[aid_dict[x]][1] for x in range(Vt.shape[1])]
    anime_ids = [aid_dict[x] for x in range(Vt.shape[1])]
    tsne_df['anime_name'] = anime_names
    tsne_df['anime_id'] = anime_ids
    tsne_df['rating'] = anime_scores
    return tsne_df

# Plotting the data: