Skip to content
The Chat Archive
mpt-30b-chat Arena Human Preference 55K

Along with Company, Cluster, show the Mean return and volatility for each company as…

  1. User

    Along with Company, Cluster, show the Mean return and volatility for each company as well.

    centroids = k_means.cluster_centers_ fig = plt.figure(figsize=(16,10)) ax = fig.add_subplot(111) scatter = ax.scatter(X.iloc[:,0],X.iloc[:,1], c = k_means.labels_, cmap ="rainbow", label = X.index) ax.set_title('k-Means') ax.set_xlabel('Mean Return') ax.set_ylabel('Volatility') plt.colorbar(scatter)

    zip joins x and y coordinates in pairs

    for x,y,name in zip(X.iloc[:,0],X.iloc[:,1],X.index):

    label = name
    
    plt.annotate(label, # this is the text
                 (x,y), # this is the point to label
                 textcoords="offset points", # how to position the text
                 xytext=(0,10), # distance from text to points (x,y)
                 ha='center') # horizontal alignment can be left, right or center
    

    plt.plot(centroids[:,0],centroids[:,1],'sg',markersize=11)

    cluster_label = pd.concat([pd.DataFrame(X.index), pd.DataFrame(k_means.labels_)],axis = 1) cluster_label.columns =['Company','Cluster'] cluster_label.sort_values(by=['Cluster'])

  2. Assistant

    To display the mean return and volatility for each company along with the cluster information, you can create a new DataFrame that includes this information and then use it to create the scatter plot. Here's an example:

    import pandas as pd
    import numpy as np
    import matplotlib.pyplot as plt
    from sklearn.datasets import make_blobs
    from sklearn.cluster import KMeans
    
    # Generate sample data
    np.random.seed(0)
    X, y = make_blobs(n_samples=100, centers=3, random_state=0, cluster_std=0.5)
    
    # Perform k-means clustering
    k_means = KMeans(n_clusters=3).fit(X)
    
    # Calculate mean return and volatility for each company
    mean_return = X[:,0]
    volatility = X[:,1]
    company_info = pd.concat([pd.DataFrame(mean_return), pd.DataFrame(volatility)], axis=1)
    company_info.index = X.index
    
    # Create scatter plot with company information
    fig, ax = plt.subplots(figsize=(16, 10))
    scatter = ax.scatter(mean_return, volatility, c=k_means.labels_, cmap="rainbow", label=X.index)
    ax.set_title('k-Means')
    ax.set_xlabel('Mean Return')
    ax.set_ylabel('Volatility')
    plt.colorbar(scatter)
    
    # Add labels for each company
    for x, y, name in zip(mean_return, volatility, X.index):
        label = name
        ax.annotate(label, (x, y), textcoords="offset points", xytext=(0, 10), ha='center')
    
    # Plot centroids
    centroids = k_means.cluster_centers_
    ax.plot(centroids[:, 0], centroids[:, 1], 'sg', markersize=11)
    
    # Add cluster information to DataFrame
    cluster_label = pd.concat([pd.DataFrame(X.index), pd.DataFrame(k_means.labels_)], axis=1)
    cluster_label.columns = ['Company', 'Cluster']
    

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.