Spaces:
Sleeping
Sleeping
File size: 3,240 Bytes
976d902 48a67eb 976d902 8bf1b11 976d902 7795094 9783e49 976d902 fd36a54 1ff0af5 976d902 380c4f4 cfd06f9 1ff0af5 cfd06f9 acc4c62 380c4f4 136a90e 380c4f4 976d902 8bf1b11 976d902 00b631c 8bf1b11 976d902 8bf1b11 976d902 136a90e 976d902 cfd06f9 976d902 b62e326 976d902 b62e326 976d902 9783e49 976d902 cfd06f9 976d902 cfd06f9 976d902 156973e 976d902 099f58f 976d902 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 |
import numpy as np
import gradio as gr
import pandas as pd
def homework01_solution1(K, X1, X2):
K = int(K)
# Verify your solutions by code
import numpy as np
X = np.array([[2.0, 5.0], [3.0, 4.0], [3.0, 2.0], [1.0, 3.0], [5.0, 2.0], [7.0, 1.0],
[6.0, 3.0], [7.0, 4.0]])
y = np.array([2.9,4.2,5.8,3.2,8.9,9.2,7.4,8.2])
import pandas as pd
train_data = pd.DataFrame(X, columns=['X1', 'X2'])
train_data['Label (Y)'] = y
from sklearn.neighbors import KNeighborsRegressor
#(1) predict class for point (3,3) with K = 3
neigh = KNeighborsRegressor(n_neighbors=K)
neigh.fit(X, y)
predicted_label = neigh.predict(np.array([[X1, X2]]))[0]
predicted_label = np.round(predicted_label, 3)
#(Q) calculate squared error
pred = neigh.predict(X)
squared_error = (pred-y)**2
#(Q2.3) evaluate mean squared error
import sklearn
y_pred = neigh.predict(X)
mse = np.round(sklearn.metrics.mean_squared_error(y,y_pred),3)
train_data['Predicted Label ('+str(K)+'-NN)'] = pred
train_data['Squaredd Error'] = squared_error
train_data['Predicted Label ('+str(K)+'-NN)'] = train_data['Predicted Label ('+str(K)+'-NN)'].round(3)
train_data['Squaredd Error'] = train_data['Squaredd Error'].round(3)
(nb_dist, nb_indice) = neigh.kneighbors(np.array([[X1, X2]]), K)
import pandas as pd
results = pd.DataFrame(columns=['Rank of closest neighbor', 'Features (X_1,X_2)', 'Label (Y)', 'Distance to query data'])
for i in range(K):
idx = nb_indice[0][i]
fea = X[idx].tolist()
fea = '({})'.format(', '.join(map(str, fea)))
dist = nb_dist[0][i]
label = y[idx]
#print(idx, fea, dist, label)
# Dictionary to append
new_data = {'Rank of closest neighbor': i, 'Features (X_1,X_2)': fea, 'Label (Y)':label , 'Distance to query data': dist}
tmp = pd.DataFrame(new_data, index=[0])
# Append dictionary to DataFrame
#data = data.append(new_data, ignore_index=True)
results = pd.concat([results, tmp], ignore_index=True)
results = results.sort_values(by='Rank of closest neighbor')
results['Distance to query data'] = results['Distance to query data'].round(3)
return train_data, results, predicted_label, mse
### configure inputs
set_K = gr.Number(value=7)
set_X1 = gr.Number(value=1)
set_X2 = gr.Number(value=2)
### configure outputs
set_output_traindata = gr.Dataframe(type='pandas', label ='Train Dataset')
set_output_q1a = gr.Dataframe(type='pandas', label ='Question 1: KNN-Regressor Search')
set_output_q1b = gr.Textbox(label ='Question 1: KNN-Regressor Prediction')
set_output_q3 = gr.Textbox(label ='Question 3: KNN-Regressor MSE (Training data)')
### configure Gradio
interface = gr.Interface(fn=homework01_solution1,
inputs=[set_K, set_X1, set_X2],
outputs=[set_output_traindata, set_output_q1a, set_output_q1b, set_output_q3],
title="CSCI4750/5750(hw01-PartI): Mathematics for KNN (Question 1 & 3: KNN-Regressor Search)",
description= "Click examples below for a quick demo",
theme = 'huggingface'
)
interface.launch(debug=True) |