UrusuLambda

var target_json = {"a":1, "b":2};

//first encoding target_json
var encoded_target_json = "data:application/json;base64,"+btoa(JSON.stringify(target_json));

//then decoding encoded_target_json
var decoded_target_json = JSON.parse(atob(encoded_target_json.replace(/^data:\w+\/\w+;base64,/, '')));

//Same as first encoding
var new_fr_json = "data:application/json;base64,"+btoa(JSON.stringify(decoded_target_json));

UrusuLambda

UrusuLambda

#For 2D
x_train_tranformed_2d = umap.UMAP(n_neighbors=5, n_components=2).fit(x_train).embedding_
x_test_tranformed_2d = umap.UMAP(n_neighbors=5, n_components=2).fit(x_test).embedding_

#For 3D
x_train_tranformed_3d = umap.UMAP(n_neighbors=5, n_components=3).fit(x_train).embedding_
x_test_tranformed_3d = umap.UMAP(n_neighbors=5, n_components=3).fit(x_test).embedding_

UrusuLambda

import tensorflow as tf
import numpy as np

#For 3D Plot
import pandas as pd
import plotly.express as px

#For PCA
from sklearn.decomposition import PCA

UrusuLambda

#For 2D
x_train_transformed_2d = TSNE(n_components=2).fit_transform(x_train)
x_test_transformed_2d = TSNE(n_components=2).fit_transform(x_test)

#For 3D
x_train_transformed_3d = TSNE(n_components=3).fit_transform(x_train)
x_test_transformed_3d = TSNE(n_components=3).fit_transform(x_test)

UrusuLambda

x_train_transformed=PCA(n_components=8).fit_transform(x_train)
x_test_transformed=PCA(n_components=8).fit_transform(x_test)

#For 2D
x_train_transformed_3d = x_train_transformed
x_test_transformed_3d = x_test_transformed

#For 3D (Same to 2d)
x_train_transformed_2d = x_train_transformed
x_test_transformed_2d = x_test_transformed

UrusuLambda

df_train=pd.DataFrame(x_train_transformed_3d[:, 0:3],columns=list("XYZ"))
df_train["label"]=np.array(y_train)
df_train['purpose'] = np.full(y_train.shape, "train")

df_test=pd.DataFrame(x_test_transformed_3d[:, 0:3],columns=list("XYZ"))
df_test["label"]=np.array(y_test)
df_test['purpose'] = np.full(y_test.shape, "test")

df_merged = pd.concat([df_train, df_test])
fig = px.scatter_3d(df_merged, x='X', y='Y', z='Z',  color='label', symbol='purpose', size_max=4, opacity=0.7)

UrusuLambda

plt.scatter(x_train_transformed_2d[:,0],x_train_transformed_2d[:,1],s=20,c=y_train,cmap='tab10', marker="o", alpha=0.3)
plt.scatter(x_test_transformed_2d[:,0],x_test_transformed_2d[:,1],s=20,c=y_test,cmap='tab10', marker="x", alpha=0.3)
plt.colorbar()

UrusuLambda

import tensorflow as tf
import numpy as np

#For 3D Plot
import pandas as pd
import plotly.express as px

#For PCA
from sklearn.decomposition import PCA

UrusuLambda

from tensorflow.keras.datasets import mnist
from sklearn.manifold import TSNE

import pandas as pd
import plotly.express as px

#load and adjust mnist data | Mnistのデータをロード
(_, _), (x_test, y_test) = mnist.load_data()
_, x_test = np.array(x_train, np.float32), np.array(x_test, np.float32)
_, x_test = x_train / 255., x_test / 255.