Kaggle Masterに学ぶ機械学習実践アプローチ 写経 01

# %%
print("hello")

# %%
import matplotlib.pyplot as plt 
import numpy as np
import pandas as pd
import seaborn as sns
from sklearn import datasets 
from sklearn import manifold 


# %%
data = datasets.fetch_openml(
    'mnist_784',
    version=1,
    return_X_y=True
)

pixel_values, targets = data 
targets = targets.astype(int)

# %%
pixel_values

# %%
single_image = pixel_values[0:1].to_numpy().reshape(28, 28)

# %%
plt.imshow(single_image, cmap='gray')

# %%
tsne = manifold.TSNE(n_components=2, random_state=42)
transformed_data = tsne.fit_transform(pixel_values.to_numpy()[:3000, : ])

# %%
tsne_df = pd.DataFrame(
    np.column_stack((transformed_data, targets[:3000])),
    columns=["x", "y", "targets"]
)
tsne_df.loc[:, "targets"] = tsne_df.targets.astype(int)

# %%
tsne_df

# %%
grid=sns.FacetGrid(tsne_df, hue="targets")
grid.map(plt.scatter, "x", "y").add_legend()

# %%