import numpy as np

import pandas as pd
from sklearn.neural_network import MLPRegressor
from sklearn.datasets import make_regression
from sklearn.model_selection import train_test_split

AL_csv=pd.read_csv("AL_seriesN.csv")

display(AL_csv.head())

Alloy Si Fe Cu Mn Mg Cr Zn Ti Zr \
0 1050 0.125 0.200 0.025 0.025 0.025 0.0 0.025 0.015 0.0
1 1060 0.125 0.175 0.025 0.015 0.015 0.0 0.025 0.015 0.0
2 1070 0.100 0.125 0.020 0.015 0.015 0.0 0.020 0.015 0.0
3 1080 0.075 0.075 0.015 0.010 0.010 0.0 0.015 0.015 0.0
4 1085 0.050 0.060 0.015 0.010 0.010 0.0 0.015 0.010 0.0

Trace element (Ga+Co+Ag+Bi+Be+Sc+B+Ni+Sn+Pb+Li+V) Al UTS

(Mpa) \
0 0.025 99.535
119.25
1 0.025 99.580
93.62
2 0.025 99.665
103.63
3 0.025 99.745
99.50
4 0.025 99.790
103.63

YS (Mpa) TE (%)
0 100.00 16.00
1 69.12 17.00
2 72.88 10.74
3 71.88 10.18
4 72.88 10.74

AL_csv.columns

Index(['Alloy', 'Si', 'Fe', 'Cu', 'Mn', 'Mg', 'Cr', 'Zn', 'Ti', 'Zr',
'Trace element (Ga+Co+Ag+Bi+Be+Sc+B+Ni+Sn+Pb+Li+V)', 'Al', 'UTS
(Mpa)',
'YS (Mpa)', 'TE (%)'],
dtype='object')

X = AL_csv.drop(['UTS (Mpa)', 'YS (Mpa)', 'TE (%)','Alloy'], axis=1)

y = AL_csv[["UTS (Mpa)", "YS (Mpa)", "TE (%)"]]

X.head(3)
 Si Fe Cu Mn Mg Cr Zn Ti Zr \
0 0.125 0.200 0.025 0.025 0.025 0.0 0.025 0.015 0.0
1 0.125 0.175 0.025 0.015 0.015 0.0 0.025 0.015 0.0
2 0.100 0.125 0.020 0.015 0.015 0.0 0.020 0.015 0.0

Trace element (Ga+Co+Ag+Bi+Be+Sc+B+Ni+Sn+Pb+Li+V) Al

0 0.025 99.535
1 0.025 99.580
2 0.025 99.665

y.head(3)

UTS (Mpa) YS (Mpa) TE (%)

0 119.25 100.00 16.00
1 93.62 69.12 17.00
2 103.63 72.88 10.74

# Replace infinity with NaN

X.replace([np.inf, -np.inf], np.nan, inplace=True)

# Fill NaN values with the column mean

X = X.fillna(X.mean())

# Split the data

X_train, X_test, y_train, y_test = train_test_split(X, y,
test_size=0.2, random_state=42)

# Normalize the data

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# Train the model

mlp = MLPRegressor(
hidden_layer_sizes=(200, 100, 50), # Increased complexity
max_iter=10000, # More iterations
learning_rate_init=0.001, # Adjusted learning rate
early_stopping=True, # Early stopping
validation_fraction=0.1, # Validation set for early
stopping
n_iter_no_change=50, # Stop if no improvement for
50 iterations
random_state=42
)
mlp.fit(X_train, y_train)

MLPRegressor(early_stopping=True, hidden_layer_sizes=(200, 100, 50),

max_iter=10000, n_iter_no_change=50, random_state=42)
 #Evaluate the model
from sklearn.metrics import mean_squared_error, r2_score
y_pred = mlp.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
print(f'Mean Squared Error: {mse}')
r2 = r2_score(y_test, y_pred)
print(f'R^2 Score: {r2}')
train_score = mlp.score(X_train, y_train)
test_score = mlp.score(X_test, y_test)
print(f"Training R^2: {train_score:.4f}")
print(f"Testing R^2: {test_score:.4f}")

Mean Squared Error: 5867.186640475095

R^2 Score: 0.14901906081596586
Training R^2: 0.2170
Testing R^2: 0.1490

import matplotlib.pyplot as plt

# Plot actual vs predicted
plt.scatter(y_test['UTS (Mpa)'], y_pred[:, 0], label='UTS (Mpa)')
plt.scatter(y_test['YS (Mpa)'], y_pred[:, 1], label='YS (Mpa)')
plt.scatter(y_test['TE (%)'], y_pred[:, 2], label='TE (%)')
plt.xlabel('Actual')
plt.ylabel('Predicted')
plt.title('Actual vs Predicted')
plt.legend()
plt.show()
with new features
X = AL_csv.drop(['UTS (Mpa)', 'YS (Mpa)', 'TE (%)','Alloy'], axis=1)
y = AL_csv[["UTS (Mpa)", "YS (Mpa)", "TE (%)"]]

X['Weighted_Sum'] = 0.265353 * X['Cu'] + 0.159489 * X['Zn'] + 0.136757

* X['Al'] + 0.094458 * X['Mg']
X['Cu_Zn_Interaction'] = X['Cu'] * X['Zn']
X['Log_Cu'] = np.log(X['Cu'] + 1)
X['Cu_to_Zn_Ratio'] = X['Cu'] / X['Zn']
X['Trace_Elements_Sum'] = X['Trace element
(Ga+Co+Ag+Bi+Be+Sc+B+Ni+Sn+Pb+Li+V)']

# Replace infinity with NaN

X.replace([np.inf, -np.inf], np.nan, inplace=True)

# Fill NaN values with the column mean

X = X.fillna(X.mean())

# Split the data

X_train, X_test, y_train, y_test = train_test_split(X, y,
test_size=0.2, random_state=42)
# Normalize the data
from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# Train the model

mlp = MLPRegressor(
hidden_layer_sizes=(200, 100, 50), # Increased complexity
max_iter=10000, # More iterations
learning_rate_init=0.001, # Adjusted learning rate
early_stopping=True, # Early stopping
validation_fraction=0.1, # Validation set for early
stopping
n_iter_no_change=50, # Stop if no improvement for
50 iterations
random_state=42
)
mlp.fit(X_train, y_train)

MLPRegressor(early_stopping=True, hidden_layer_sizes=(200, 100, 50),

max_iter=10000, n_iter_no_change=50, random_state=42)

#Evaluate the model

from sklearn.metrics import mean_squared_error, r2_score
y_pred = mlp.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
print(f'Mean Squared Error: {mse}')
r2 = r2_score(y_test, y_pred)
print(f'R^2 Score: {r2}')
train_score = mlp.score(X_train, y_train)
test_score = mlp.score(X_test, y_test)
print(f"Training R^2: {train_score:.4f}")
print(f"Testing R^2: {test_score:.4f}")

Mean Squared Error: 5331.229923952499

R^2 Score: 0.17351464768811006
Training R^2: 0.3370
Testing R^2: 0.1735

import matplotlib.pyplot as plt

# Plot actual vs predicted
plt.scatter(y_test['UTS (Mpa)'], y_pred[:, 0], label='UTS (Mpa)')
plt.scatter(y_test['YS (Mpa)'], y_pred[:, 1], label='YS (Mpa)')
plt.scatter(y_test['TE (%)'], y_pred[:, 2], label='TE (%)')
plt.xlabel('Actual')
plt.ylabel('Predicted')
plt.title('Actual vs Predicted')
plt.legend()
plt.show()

with hyperparamter tuning

X = AL_csv.drop(['UTS (Mpa)', 'YS (Mpa)', 'TE (%)','Alloy'], axis=1)
y = AL_csv[["UTS (Mpa)", "YS (Mpa)", "TE (%)"]]

# Split the data

X_train, X_test, y_train, y_test = train_test_split(X, y,
test_size=0.2, random_state=42)

# Normalize the data

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# Train the model

mlp = MLPRegressor(
hidden_layer_sizes=(50, 25), # Two hidden layers
activation='relu', # ReLU activation
 solver='adam', # Use Adam solver
alpha=0.001, # Regularization strength
learning_rate_init=0.001, # Initial learning rate
max_iter=1000, # Increase max iterations
early_stopping=True, # Enable early stopping
validation_fraction=0.2, # 20% validation data
n_iter_no_change=10, # Stop if no improvement for 10
epochs
random_state=42, # Reproducibility
verbose=True # Monitor training progress
)
mlp.fit(X_train, y_train)

Iteration 1, loss = 31685.53270493

Validation score: -4.271692
Iteration 2, loss = 31675.63089445
Validation score: -4.271575
Iteration 3, loss = 31665.66221233
Validation score: -4.271310
Iteration 4, loss = 31655.63073756
Validation score: -4.271009
Iteration 5, loss = 31645.54923466
Validation score: -4.270644
Iteration 6, loss = 31635.38447279
Validation score: -4.270310
Iteration 7, loss = 31625.10497769
Validation score: -4.270041
Iteration 8, loss = 31614.74482908
Validation score: -4.269689
Iteration 9, loss = 31604.28143496
Validation score: -4.269078
Iteration 10, loss = 31593.77337621
Validation score: -4.268418
Iteration 11, loss = 31583.12489926
Validation score: -4.267487
Iteration 12, loss = 31572.36598410
Validation score: -4.266154
Iteration 13, loss = 31561.50451117
Validation score: -4.264910
Iteration 14, loss = 31550.53057331
Validation score: -4.263520
Iteration 15, loss = 31539.41808163
Validation score: -4.261786
Iteration 16, loss = 31528.13222853
Validation score: -4.259949
Iteration 17, loss = 31516.77906113
Validation score: -4.257890
Iteration 18, loss = 31505.34617029
Validation score: -4.255369
Iteration 19, loss = 31493.78082560
Validation score: -4.252544
Iteration 20, loss = 31482.04976564
Validation score: -4.249659
Iteration 21, loss = 31470.10547801
Validation score: -4.246788
Iteration 22, loss = 31457.93865898
Validation score: -4.243773
Iteration 23, loss = 31445.55333200
Validation score: -4.240528
Iteration 24, loss = 31432.92936649
Validation score: -4.237142
Iteration 25, loss = 31420.09422817
Validation score: -4.233702
Iteration 26, loss = 31406.96941585
Validation score: -4.230038
Iteration 27, loss = 31393.57205349
Validation score: -4.226048
Iteration 28, loss = 31379.91008807
Validation score: -4.221839
Iteration 29, loss = 31365.93880976
Validation score: -4.217439
Iteration 30, loss = 31351.63377730
Validation score: -4.212593
Iteration 31, loss = 31336.95327528
Validation score: -4.207405
Iteration 32, loss = 31321.93159309
Validation score: -4.201889
Iteration 33, loss = 31306.56216899
Validation score: -4.196158
Iteration 34, loss = 31290.82336928
Validation score: -4.190175
Iteration 35, loss = 31274.72224026
Validation score: -4.183901
Iteration 36, loss = 31258.25070654
Validation score: -4.177235
Iteration 37, loss = 31241.39874513
Validation score: -4.170245
Iteration 38, loss = 31224.18684287
Validation score: -4.162943
Iteration 39, loss = 31206.59692237
Validation score: -4.155261
Iteration 40, loss = 31188.56854807
Validation score: -4.147250
Iteration 41, loss = 31170.08012217
Validation score: -4.138726
Iteration 42, loss = 31151.10208309
Validation score: -4.129681
Iteration 43, loss = 31131.65490277
Validation score: -4.120269
Iteration 44, loss = 31111.70722541
Validation score: -4.110433
Iteration 45, loss = 31091.29705621
Validation score: -4.100200
Iteration 46, loss = 31070.38281370
Validation score: -4.089578
Iteration 47, loss = 31048.94746520
Validation score: -4.078565
Iteration 48, loss = 31026.99486747
Validation score: -4.067158
Iteration 49, loss = 31004.51099799
Validation score: -4.055246
Iteration 50, loss = 30981.47017937
Validation score: -4.042830
Iteration 51, loss = 30957.84267963
Validation score: -4.029959
Iteration 52, loss = 30933.63287754
Validation score: -4.016640
Iteration 53, loss = 30908.79514815
Validation score: -4.002874
Iteration 54, loss = 30883.33520934
Validation score: -3.988537
Iteration 55, loss = 30857.24154561
Validation score: -3.973622
Iteration 56, loss = 30830.51321910
Validation score: -3.958235
Iteration 57, loss = 30803.12858028
Validation score: -3.942458
Iteration 58, loss = 30775.02328534
Validation score: -3.925876
Iteration 59, loss = 30746.19794413
Validation score: -3.908675
Iteration 60, loss = 30716.64510722
Validation score: -3.890968
Iteration 61, loss = 30686.26955168
Validation score: -3.872822
Iteration 62, loss = 30655.04806415
Validation score: -3.854223
Iteration 63, loss = 30623.08085126
Validation score: -3.835096
Iteration 64, loss = 30590.35797233
Validation score: -3.815548
Iteration 65, loss = 30556.82915660
Validation score: -3.795669
Iteration 66, loss = 30522.48515515
Validation score: -3.775323
Iteration 67, loss = 30487.34476132
Validation score: -3.754550
Iteration 68, loss = 30451.38447017
Validation score: -3.733337
Iteration 69, loss = 30414.55850801
Validation score: -3.711706
Iteration 70, loss = 30376.86003141
Validation score: -3.689658
Iteration 71, loss = 30338.25909143
Validation score: -3.667231
Iteration 72, loss = 30298.77358770
Validation score: -3.644452
Iteration 73, loss = 30258.35723178
Validation score: -3.621232
Iteration 74, loss = 30217.00509107
Validation score: -3.597560
Iteration 75, loss = 30174.74087914
Validation score: -3.573494
Iteration 76, loss = 30131.48847549
Validation score: -3.549011
Iteration 77, loss = 30087.24772517
Validation score: -3.524093
Iteration 78, loss = 30042.03590269
Validation score: -3.498755
Iteration 79, loss = 29995.78356439
Validation score: -3.473012
Iteration 80, loss = 29948.47491901
Validation score: -3.446922
Iteration 81, loss = 29900.14639944
Validation score: -3.420447
Iteration 82, loss = 29850.76830258
Validation score: -3.393503
Iteration 83, loss = 29800.34218872
Validation score: -3.366215
Iteration 84, loss = 29748.86540582
Validation score: -3.338598
Iteration 85, loss = 29696.32093175
Validation score: -3.310659
Iteration 86, loss = 29642.67816190
Validation score: -3.282403
Iteration 87, loss = 29587.93573729
Validation score: -3.253916
Iteration 88, loss = 29532.03511509
Validation score: -3.225187
Iteration 89, loss = 29474.94327553
Validation score: -3.196218
Iteration 90, loss = 29416.50630370
Validation score: -3.167018
Iteration 91, loss = 29356.76277131
Validation score: -3.137574
Iteration 92, loss = 29295.77408952
Validation score: -3.107979
Iteration 93, loss = 29233.46254133
Validation score: -3.078221
Iteration 94, loss = 29169.72558996
Validation score: -3.048313
Iteration 95, loss = 29104.65987656
Validation score: -3.018251
Iteration 96, loss = 29038.29081352
Validation score: -2.988108
Iteration 97, loss = 28970.60892944
Validation score: -2.957820
Iteration 98, loss = 28901.60731164
Validation score: -2.927349
Iteration 99, loss = 28831.26483238
Validation score: -2.896888
Iteration 100, loss = 28759.53518740
Validation score: -2.866452
Iteration 101, loss = 28686.38961130
Validation score: -2.836105
Iteration 102, loss = 28611.89062671
Validation score: -2.805794
Iteration 103, loss = 28535.99772874
Validation score: -2.775650
Iteration 104, loss = 28458.68745190
Validation score: -2.745715
Iteration 105, loss = 28379.95359308
Validation score: -2.716033
Iteration 106, loss = 28299.80417455
Validation score: -2.686617
Iteration 107, loss = 28218.16435722
Validation score: -2.657446
Iteration 108, loss = 28135.06490117
Validation score: -2.628639
Iteration 109, loss = 28050.42305742
Validation score: -2.600234
Iteration 110, loss = 27964.27479303
Validation score: -2.572230
Iteration 111, loss = 27876.64587644
Validation score: -2.544716
Iteration 112, loss = 27787.47360170
Validation score: -2.517733
Iteration 113, loss = 27696.75166465
Validation score: -2.491353
Iteration 114, loss = 27604.53394064
Validation score: -2.465616
Iteration 115, loss = 27510.80868329
Validation score: -2.440551
Iteration 116, loss = 27415.52806317
Validation score: -2.416177
Iteration 117, loss = 27318.69937269
Validation score: -2.392529
Iteration 118, loss = 27220.31200172
Validation score: -2.369586
Iteration 119, loss = 27120.30528166
Validation score: -2.347417
Iteration 120, loss = 27018.64466741
Validation score: -2.326015
Iteration 121, loss = 26915.40016538
Validation score: -2.305332
Iteration 122, loss = 26810.58718131
Validation score: -2.285269
Iteration 123, loss = 26704.19189862
Validation score: -2.266013
Iteration 124, loss = 26596.21756369
Validation score: -2.247568
Iteration 125, loss = 26486.66863583
Validation score: -2.229917
Iteration 126, loss = 26375.49288490
Validation score: -2.213043
Iteration 127, loss = 26262.70103930
Validation score: -2.196947
Iteration 128, loss = 26148.29924146
Validation score: -2.181579
Iteration 129, loss = 26032.31786392
Validation score: -2.166902
Iteration 130, loss = 25914.74991090
Validation score: -2.152870
Iteration 131, loss = 25795.54791052
Validation score: -2.139436
Iteration 132, loss = 25674.67658435
Validation score: -2.126520
Iteration 133, loss = 25552.19516953
Validation score: -2.114060
Iteration 134, loss = 25428.01587465
Validation score: -2.102055
Iteration 135, loss = 25302.18702586
Validation score: -2.090446
Iteration 136, loss = 25174.76871675
Validation score: -2.079128
Iteration 137, loss = 25045.76865197
Validation score: -2.068018
Iteration 138, loss = 24915.15717621
Validation score: -2.057053
Iteration 139, loss = 24782.94928738
Validation score: -2.046176
Iteration 140, loss = 24649.09056764
Validation score: -2.035341
Iteration 141, loss = 24513.61631012
Validation score: -2.024503
Iteration 142, loss = 24376.54018435
Validation score: -2.013611
Iteration 143, loss = 24237.81566799
Validation score: -2.002644
Iteration 144, loss = 24097.48815756
Validation score: -1.991573
Iteration 145, loss = 23955.59073043
Validation score: -1.980371
Iteration 146, loss = 23812.13224238
Validation score: -1.969015
Iteration 147, loss = 23667.06118671
Validation score: -1.957488
Iteration 148, loss = 23520.42322425
Validation score: -1.945761
Iteration 149, loss = 23372.25168086
Validation score: -1.933827
Iteration 150, loss = 23222.52945274
Validation score: -1.921833
Iteration 151, loss = 23071.33585140
Validation score: -1.909644
Iteration 152, loss = 22918.68861353
Validation score: -1.897269
Iteration 153, loss = 22764.60776502
Validation score: -1.884717
Iteration 154, loss = 22609.02540374
Validation score: -1.872007
Iteration 155, loss = 22452.01636085
Validation score: -1.859148
Iteration 156, loss = 22293.61358909
Validation score: -1.846190
Iteration 157, loss = 22133.83085129
Validation score: -1.833295
Iteration 158, loss = 21972.69591089
Validation score: -1.820295
Iteration 159, loss = 21810.25554546
Validation score: -1.807213
Iteration 160, loss = 21646.46930914
Validation score: -1.794094
Iteration 161, loss = 21481.39476522
Validation score: -1.780999
Iteration 162, loss = 21315.06101274
Validation score: -1.767926
Iteration 163, loss = 21147.47739720
Validation score: -1.754853
Iteration 164, loss = 20978.71257003
Validation score: -1.741953
Iteration 165, loss = 20808.77668744
Validation score: -1.729144
Iteration 166, loss = 20637.72746305
Validation score: -1.716416
Iteration 167, loss = 20465.59615314
Validation score: -1.703731
Iteration 168, loss = 20292.36484539
Validation score: -1.691131
Iteration 169, loss = 20118.05513662
Validation score: -1.678642
Iteration 170, loss = 19942.74321998
Validation score: -1.666300
Iteration 171, loss = 19766.40282067
Validation score: -1.654100
Iteration 172, loss = 19589.08606561
Validation score: -1.642085
Iteration 173, loss = 19410.77508779
Validation score: -1.630264
Iteration 174, loss = 19231.57363725
Validation score: -1.618609
Iteration 175, loss = 19051.53734083
Validation score: -1.607133
Iteration 176, loss = 18870.72968060
Validation score: -1.595862
Iteration 177, loss = 18689.11334970
Validation score: -1.584794
Iteration 178, loss = 18506.66489697
Validation score: -1.573871
Iteration 179, loss = 18323.49383031
Validation score: -1.563054
Iteration 180, loss = 18139.62839454
Validation score: -1.552389
Iteration 181, loss = 17955.14320928
Validation score: -1.541855
Iteration 182, loss = 17769.97282214
Validation score: -1.531414
Iteration 183, loss = 17584.05193483
Validation score: -1.521030
Iteration 184, loss = 17397.62559279
Validation score: -1.510705
Iteration 185, loss = 17210.61613784
Validation score: -1.500429
Iteration 186, loss = 17023.14511247
Validation score: -1.490096
Iteration 187, loss = 16835.36934970
Validation score: -1.479653
Iteration 188, loss = 16647.35190309
Validation score: -1.469067
Iteration 189, loss = 16459.13424228
Validation score: -1.458294
Iteration 190, loss = 16270.76782648
Validation score: -1.447281
Iteration 191, loss = 16082.27707310
Validation score: -1.436011
Iteration 192, loss = 15893.24548085
Validation score: -1.424480
Iteration 193, loss = 15704.16547562
Validation score: -1.412659
Iteration 194, loss = 15515.08867722
Validation score: -1.400500
Iteration 195, loss = 15326.12080538
Validation score: -1.387916
Iteration 196, loss = 15137.32651188
Validation score: -1.374893
Iteration 197, loss = 14948.69306443
Validation score: -1.361448
Iteration 198, loss = 14760.22567611
Validation score: -1.347568
Iteration 199, loss = 14572.11426868
Validation score: -1.333340
Iteration 200, loss = 14384.28940425
Validation score: -1.318749
Iteration 201, loss = 14196.67025453
Validation score: -1.303799
Iteration 202, loss = 14009.54982877
Validation score: -1.288567
Iteration 203, loss = 13823.01453107
Validation score: -1.273090
Iteration 204, loss = 13637.12484807
Validation score: -1.257404
Iteration 205, loss = 13451.90937689
Validation score: -1.241540
Iteration 206, loss = 13267.43112028
Validation score: -1.225522
Iteration 207, loss = 13083.55549613
Validation score: -1.209391
Iteration 208, loss = 12900.44191054
Validation score: -1.193213
Iteration 209, loss = 12718.26673361
Validation score: -1.177006
Iteration 210, loss = 12537.02041590
Validation score: -1.160790
Iteration 211, loss = 12356.77702539
Validation score: -1.144643
Iteration 212, loss = 12177.56026696
Validation score: -1.128604
Iteration 213, loss = 11999.39071022
Validation score: -1.112669
Iteration 214, loss = 11822.39502565
Validation score: -1.096884
Iteration 215, loss = 11646.64111126
Validation score: -1.081287
Iteration 216, loss = 11472.18810737
Validation score: -1.065903
Iteration 217, loss = 11299.07063583
Validation score: -1.050800
Iteration 218, loss = 11127.30739029
Validation score: -1.035946
Iteration 219, loss = 10956.93426984
Validation score: -1.021361
Iteration 220, loss = 10788.02399100
Validation score: -1.007055
Iteration 221, loss = 10620.64166889
Validation score: -0.993026
Iteration 222, loss = 10454.84171036
Validation score: -0.979268
Iteration 223, loss = 10290.57921494
Validation score: -0.965788
Iteration 224, loss = 10127.97421017
Validation score: -0.952613
Iteration 225, loss = 9967.00945138
Validation score: -0.939669
Iteration 226, loss = 9807.70863819
Validation score: -0.926932
Iteration 227, loss = 9650.16121496
Validation score: -0.914387
Iteration 228, loss = 9494.34294281
Validation score: -0.902009
Iteration 229, loss = 9340.34017715
Validation score: -0.889728
Iteration 230, loss = 9188.17654103
Validation score: -0.877584
Iteration 231, loss = 9037.92813239
Validation score: -0.865575
Iteration 232, loss = 8889.64154763
Validation score: -0.853685
Iteration 233, loss = 8743.32238751
Validation score: -0.841883
Iteration 234, loss = 8599.05372342
Validation score: -0.830151
Iteration 235, loss = 8456.84111549
Validation score: -0.818473
Iteration 236, loss = 8316.69123394
Validation score: -0.806854
Iteration 237, loss = 8178.56440549
Validation score: -0.795285
Iteration 238, loss = 8042.53809250
Validation score: -0.783770
Iteration 239, loss = 7908.44457677
Validation score: -0.772314
Iteration 240, loss = 7776.47874917
Validation score: -0.760940
Iteration 241, loss = 7646.66625138
Validation score: -0.749665
Iteration 242, loss = 7518.80714393
Validation score: -0.738505
Iteration 243, loss = 7393.08167683
Validation score: -0.727496
Iteration 244, loss = 7269.51498472
Validation score: -0.716645
Iteration 245, loss = 7148.13163757
Validation score: -0.705972
Iteration 246, loss = 7028.91739864
Validation score: -0.695498
Iteration 247, loss = 6911.91739156
Validation score: -0.685242
Iteration 248, loss = 6797.11730185
Validation score: -0.675193
Iteration 249, loss = 6684.52079189
Validation score: -0.665366
Iteration 250, loss = 6574.14338065
Validation score: -0.655790
Iteration 251, loss = 6465.98853336
Validation score: -0.646466
Iteration 252, loss = 6359.95916930
Validation score: -0.637406
Iteration 253, loss = 6256.12447143
Validation score: -0.628612
Iteration 254, loss = 6154.47335191
Validation score: -0.620078
Iteration 255, loss = 6055.00433619
Validation score: -0.611780
Iteration 256, loss = 5957.71085364
Validation score: -0.603723
Iteration 257, loss = 5862.59277872
Validation score: -0.595907
Iteration 258, loss = 5769.62880280
Validation score: -0.588320
Iteration 259, loss = 5678.80335163
Validation score: -0.580950
Iteration 260, loss = 5590.10384213
Validation score: -0.573784
Iteration 261, loss = 5503.51492211
Validation score: -0.566810
Iteration 262, loss = 5419.01711256
Validation score: -0.560018
Iteration 263, loss = 5336.58699660
Validation score: -0.553396
Iteration 264, loss = 5256.17996414
Validation score: -0.546937
Iteration 265, loss = 5177.76233430
Validation score: -0.540637
Iteration 266, loss = 5101.32151618
Validation score: -0.534442
Iteration 267, loss = 5026.82118756
Validation score: -0.528239
Iteration 268, loss = 4954.23325177
Validation score: -0.522186
Iteration 269, loss = 4883.50607379
Validation score: -0.516283
Iteration 270, loss = 4814.63819329
Validation score: -0.510537
Iteration 271, loss = 4747.61059622
Validation score: -0.504956
Iteration 272, loss = 4682.39576069
Validation score: -0.499545
Iteration 273, loss = 4618.96319940
Validation score: -0.494312
Iteration 274, loss = 4557.28216694
Validation score: -0.489259
Iteration 275, loss = 4497.31922794
Validation score: -0.484262
Iteration 276, loss = 4439.03822297
Validation score: -0.479419
Iteration 277, loss = 4382.40112900
Validation score: -0.474768
Iteration 278, loss = 4327.37287951
Validation score: -0.470314
Iteration 279, loss = 4273.91366573
Validation score: -0.466043
Iteration 280, loss = 4222.01073595
Validation score: -0.461951
Iteration 281, loss = 4171.61377802
Validation score: -0.457921
Iteration 282, loss = 4122.68759368
Validation score: -0.454070
Iteration 283, loss = 4075.20460017
Validation score: -0.450391
Iteration 284, loss = 4029.13457051
Validation score: -0.446875
Iteration 285, loss = 3984.44134203
Validation score: -0.443513
Iteration 286, loss = 3941.08963806
Validation score: -0.440298
Iteration 287, loss = 3899.04621336
Validation score: -0.437224
Iteration 288, loss = 3858.27646406
Validation score: -0.434191
Iteration 289, loss = 3818.74268623
Validation score: -0.431254
Iteration 290, loss = 3780.38678789
Validation score: -0.428441
Iteration 291, loss = 3743.11444231
Validation score: -0.425755
Iteration 292, loss = 3706.95328781
Validation score: -0.423163
Iteration 293, loss = 3671.87142135
Validation score: -0.420617
Iteration 294, loss = 3637.83398541
Validation score: -0.418191
Iteration 295, loss = 3604.83830880
Validation score: -0.415887
Iteration 296, loss = 3572.87468737
Validation score: -0.413706
Iteration 297, loss = 3541.87114472
Validation score: -0.411649
Iteration 298, loss = 3511.79470308
Validation score: -0.409669
Iteration 299, loss = 3482.60895260
Validation score: -0.407811
Iteration 300, loss = 3454.27740990
Validation score: -0.406073
Iteration 301, loss = 3426.77694982
Validation score: -0.404451
Iteration 302, loss = 3400.10205584
Validation score: -0.402941
Iteration 303, loss = 3374.21791701
Validation score: -0.401538
Iteration 304, loss = 3349.00037177
Validation score: -0.400242
Iteration 305, loss = 3324.49293503
Validation score: -0.399046
Iteration 306, loss = 3300.73346067
Validation score: -0.397954
Iteration 307, loss = 3277.65317445
Validation score: -0.396961
Iteration 308, loss = 3255.25003554
Validation score: -0.396063
Iteration 309, loss = 3233.47300488
Validation score: -0.395256
Iteration 310, loss = 3212.29771045
Validation score: -0.394532
Iteration 311, loss = 3191.69704313
Validation score: -0.393888
Iteration 312, loss = 3171.65571113
Validation score: -0.393319
Iteration 313, loss = 3152.15168757
Validation score: -0.392824
Iteration 314, loss = 3133.16760140
Validation score: -0.392406
Iteration 315, loss = 3114.68987352
Validation score: -0.392057
Iteration 316, loss = 3096.70248943
Validation score: -0.391776
Iteration 317, loss = 3079.18887649
Validation score: -0.391557
Iteration 318, loss = 3062.15144083
Validation score: -0.391396
Iteration 319, loss = 3045.61606234
Validation score: -0.391292
Iteration 320, loss = 3029.51862114
Validation score: -0.391243
Iteration 321, loss = 3013.82281466
Validation score: -0.391248
Iteration 322, loss = 2998.51568809
Validation score: -0.391279
Iteration 323, loss = 2983.58671260
Validation score: -0.391365
Iteration 324, loss = 2969.04525624
Validation score: -0.391502
Iteration 325, loss = 2954.91532521
Validation score: -0.391676
Iteration 326, loss = 2941.11803195
Validation score: -0.391897
Iteration 327, loss = 2927.64499804
Validation score: -0.392165
Iteration 328, loss = 2914.47752686
Validation score: -0.392477
Iteration 329, loss = 2901.61311379
Validation score: -0.392833
Iteration 330, loss = 2889.06583080
Validation score: -0.393234
Validation score did not improve more than tol=0.000100 for 10
consecutive epochs. Stopping.

MLPRegressor(alpha=0.001, early_stopping=True, hidden_layer_sizes=(50,

25),
max_iter=1000, random_state=42, validation_fraction=0.2,
verbose=True)

#Evaluate the model

from sklearn.metrics import mean_squared_error
y_pred = mlp.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
print(f'Mean Squared Error: {mse}')
train_score = mlp.score(X_train, y_train)
test_score = mlp.score(X_test, y_test)
print(f"Training R^2: {train_score:.4f}")
print(f"Testing R^2: {test_score:.4f}")

Mean Squared Error: 8971.311435577689

Training R^2: 0.1129
Testing R^2: -0.1902

from sklearn.model_selection import GridSearchCV

# Define the parameter grid

param_grid = {
'hidden_layer_sizes': [(50,), (50, 25), (100, 50)],
'alpha': [0.0001, 0.001, 0.01],
'learning_rate_init': [0.001, 0.01, 0.1],
'solver': ['adam', 'lbfgs']
}

# Initialize GridSearchCV
grid_search = GridSearchCV(
estimator=MLPRegressor(max_iter=10000, early_stopping=True,
random_state=42),
param_grid=param_grid,
cv=5, # 5-fold cross-validation
scoring='neg_mean_squared_error',
verbose=2
)

# Fit the model

grid_search.fit(X_train, y_train)

# Best parameters
print("Best Parameters:", grid_search.best_params_)

Fitting 5 folds for each of 54 candidates, totalling 270 fits

[CV] END alpha=0.0001, hidden_layer_sizes=(50,),
learning_rate_init=0.001, solver=adam; total time= 1.5s
[CV] END alpha=0.0001, hidden_layer_sizes=(50,),
learning_rate_init=0.001, solver=adam; total time= 1.3s
[CV] END alpha=0.0001, hidden_layer_sizes=(50,),
learning_rate_init=0.001, solver=adam; total time= 1.9s
[CV] END alpha=0.0001, hidden_layer_sizes=(50,),
learning_rate_init=0.001, solver=adam; total time= 2.1s
[CV] END alpha=0.0001, hidden_layer_sizes=(50,),
learning_rate_init=0.001, solver=adam; total time= 1.8s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50,),

learning_rate_init=0.001, solver=lbfgs; total time= 3.8s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50,),

learning_rate_init=0.001, solver=lbfgs; total time= 4.0s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50,),

learning_rate_init=0.001, solver=lbfgs; total time= 4.1s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50,),

learning_rate_init=0.001, solver=lbfgs; total time= 3.7s
C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50,),

learning_rate_init=0.001, solver=lbfgs; total time= 3.8s
[CV] END alpha=0.0001, hidden_layer_sizes=(50,),
learning_rate_init=0.01, solver=adam; total time= 0.1s
[CV] END alpha=0.0001, hidden_layer_sizes=(50,),
learning_rate_init=0.01, solver=adam; total time= 0.0s
[CV] END alpha=0.0001, hidden_layer_sizes=(50,),
learning_rate_init=0.01, solver=adam; total time= 0.1s
[CV] END alpha=0.0001, hidden_layer_sizes=(50,),
learning_rate_init=0.01, solver=adam; total time= 0.0s
[CV] END alpha=0.0001, hidden_layer_sizes=(50,),
learning_rate_init=0.01, solver=adam; total time= 0.2s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50,),

learning_rate_init=0.01, solver=lbfgs; total time= 4.1s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50,),

learning_rate_init=0.01, solver=lbfgs; total time= 4.1s
C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50,),

learning_rate_init=0.01, solver=lbfgs; total time= 4.1s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50,),

learning_rate_init=0.01, solver=lbfgs; total time= 3.9s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50,),

learning_rate_init=0.01, solver=lbfgs; total time= 4.2s
[CV] END alpha=0.0001, hidden_layer_sizes=(50,),
learning_rate_init=0.1, solver=adam; total time= 0.0s
[CV] END alpha=0.0001, hidden_layer_sizes=(50,),
learning_rate_init=0.1, solver=adam; total time= 0.0s
[CV] END alpha=0.0001, hidden_layer_sizes=(50,),
learning_rate_init=0.1, solver=adam; total time= 0.0s
[CV] END alpha=0.0001, hidden_layer_sizes=(50,),
learning_rate_init=0.1, solver=adam; total time= 0.0s
[CV] END alpha=0.0001, hidden_layer_sizes=(50,),
learning_rate_init=0.1, solver=adam; total time= 0.0s
C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50,),

learning_rate_init=0.1, solver=lbfgs; total time= 4.1s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50,),

learning_rate_init=0.1, solver=lbfgs; total time= 3.7s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50,),

learning_rate_init=0.1, solver=lbfgs; total time= 4.7s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
 self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50,),

learning_rate_init=0.1, solver=lbfgs; total time= 4.0s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50,),

learning_rate_init=0.1, solver=lbfgs; total time= 3.8s
[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),
learning_rate_init=0.001, solver=adam; total time= 0.8s
[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),
learning_rate_init=0.001, solver=adam; total time= 0.9s
[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),
learning_rate_init=0.001, solver=adam; total time= 0.8s
[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),
learning_rate_init=0.001, solver=adam; total time= 0.9s
[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),
learning_rate_init=0.001, solver=adam; total time= 0.2s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),

learning_rate_init=0.001, solver=lbfgs; total time= 6.7s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
 https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),

learning_rate_init=0.001, solver=lbfgs; total time= 6.2s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),

learning_rate_init=0.001, solver=lbfgs; total time= 8.4s
[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),
learning_rate_init=0.001, solver=lbfgs; total time= 5.0s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),

learning_rate_init=0.001, solver=lbfgs; total time= 8.8s
[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),
learning_rate_init=0.01, solver=adam; total time= 0.0s
[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),
learning_rate_init=0.01, solver=adam; total time= 0.0s
[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),
learning_rate_init=0.01, solver=adam; total time= 0.0s
[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),
learning_rate_init=0.01, solver=adam; total time= 0.0s
[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),
learning_rate_init=0.01, solver=adam; total time= 0.0s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
Increase the number of iterations (max_iter) or scale the data as
shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),

learning_rate_init=0.01, solver=lbfgs; total time= 7.8s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),

learning_rate_init=0.01, solver=lbfgs; total time= 5.8s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),

learning_rate_init=0.01, solver=lbfgs; total time= 6.4s
[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),
learning_rate_init=0.01, solver=lbfgs; total time= 3.6s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)
[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),
learning_rate_init=0.01, solver=lbfgs; total time= 5.9s
[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),
learning_rate_init=0.1, solver=adam; total time= 0.0s
[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),
learning_rate_init=0.1, solver=adam; total time= 0.0s
[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),
learning_rate_init=0.1, solver=adam; total time= 0.0s
[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),
learning_rate_init=0.1, solver=adam; total time= 0.0s
[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),
learning_rate_init=0.1, solver=adam; total time= 0.0s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),

learning_rate_init=0.1, solver=lbfgs; total time= 6.4s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),

learning_rate_init=0.1, solver=lbfgs; total time= 6.4s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)
[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),
learning_rate_init=0.1, solver=lbfgs; total time= 7.7s
[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),
learning_rate_init=0.1, solver=lbfgs; total time= 5.5s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(50, 25),

learning_rate_init=0.1, solver=lbfgs; total time= 9.2s
[CV] END alpha=0.0001, hidden_layer_sizes=(100, 50),
learning_rate_init=0.001, solver=adam; total time= 0.0s
[CV] END alpha=0.0001, hidden_layer_sizes=(100, 50),
learning_rate_init=0.001, solver=adam; total time= 0.0s
[CV] END alpha=0.0001, hidden_layer_sizes=(100, 50),
learning_rate_init=0.001, solver=adam; total time= 0.0s
[CV] END alpha=0.0001, hidden_layer_sizes=(100, 50),
learning_rate_init=0.001, solver=adam; total time= 0.0s
[CV] END alpha=0.0001, hidden_layer_sizes=(100, 50),
learning_rate_init=0.001, solver=adam; total time= 0.0s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(100, 50),

learning_rate_init=0.001, solver=lbfgs; total time= 12.5s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
 self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(100, 50),

learning_rate_init=0.001, solver=lbfgs; total time= 12.7s

C:\Users\user\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:545: ConvergenceWarning:
lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as

shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)

[CV] END alpha=0.0001, hidden_layer_sizes=(100, 50),

learning_rate_init=0.001, solver=lbfgs; total time= 12.9s

----------------------------------------------------------------------
-----
KeyboardInterrupt Traceback (most recent call
last)
Cell In[26], line 21
12 grid_search = GridSearchCV(
13 estimator=MLPRegressor(max_iter=10000,
early_stopping=True, random_state=42),
14 param_grid=param_grid,
(...)
17 verbose=2
18 )
20 # Fit the model
---> 21 grid_search.fit(X_train, y_train)
23 # Best parameters
24 print("Best Parameters:", grid_search.best_params_)

File ~\AppData\Roaming\Python\Python312\site-packages\sklearn\
base.py:1473, in
_fit_context.<locals>.decorator.<locals>.wrapper(estimator, *args,
**kwargs)
1466 estimator._validate_params()
1468 with config_context(
1469 skip_parameter_validation=(
1470 prefer_skip_nested_validation or
global_skip_validation
1471 )
1472 ):
-> 1473 return fit_method(estimator, *args, **kwargs)
File ~\AppData\Roaming\Python\Python312\site-packages\sklearn\
model_selection\_search.py:1018, in BaseSearchCV.fit(self, X, y,
**params)
1012 results = self._format_results(
1013 all_candidate_params, n_splits, all_out,
all_more_results
1014 )
1016 return results
-> 1018 self._run_search(evaluate_candidates)
1020 # multimetric is determined here because in the case of a
callable
1021 # self.scoring the return type is only known after calling
1022 first_test_score = all_out[0]["test_scores"]

File ~\AppData\Roaming\Python\Python312\site-packages\sklearn\
model_selection\_search.py:1572, in GridSearchCV._run_search(self,
evaluate_candidates)
1570 def _run_search(self, evaluate_candidates):
1571 """Search all candidates in param_grid"""
-> 1572 evaluate_candidates(ParameterGrid(self.param_grid))

File ~\AppData\Roaming\Python\Python312\site-packages\sklearn\
model_selection\_search.py:964, in
BaseSearchCV.fit.<locals>.evaluate_candidates(candidate_params, cv,
more_results)
956 if self.verbose > 0:
957 print(
958 "Fitting {0} folds for each of {1} candidates,"
959 " totalling {2} fits".format(
960 n_splits, n_candidates, n_candidates * n_splits
961 )
962 )
--> 964 out = parallel(
965 delayed(_fit_and_score)(
966 clone(base_estimator),
967 X,
968 y,
969 train=train,
970 test=test,
971 parameters=parameters,
972 split_progress=(split_idx, n_splits),
973 candidate_progress=(cand_idx, n_candidates),
974 **fit_and_score_kwargs,
975 )
976 for (cand_idx, parameters), (split_idx, (train, test)) in
product(
977 enumerate(candidate_params),
978 enumerate(cv.split(X, y,
**routed_params.splitter.split)),
 979 )
980 )
982 if len(out) < 1:
983 raise ValueError(
984 "No fits were performed. "
985 "Was the CV iterator empty? "
986 "Were there no candidates?"
987 )

File ~\AppData\Roaming\Python\Python312\site-packages\sklearn\utils\
parallel.py:74, in Parallel.__call__(self, iterable)
69 config = get_config()
70 iterable_with_config = (
71 (_with_config(delayed_func, config), args, kwargs)
72 for delayed_func, args, kwargs in iterable
73 )
---> 74 return super().__call__(iterable_with_config)

File ~\anaconda3\Lib\site-packages\joblib\parallel.py:1918, in
Parallel.__call__(self, iterable)
1916 output = self._get_sequential_output(iterable)
1917 next(output)
-> 1918 return output if self.return_generator else list(output)
1920 # Let's create an ID that uniquely identifies the current
call. If the
1921 # call is interrupted early and that the same instance is
immediately
1922 # re-used, this id will be used to prevent workers that were
1923 # concurrently finalizing a task from the previous call to run
the
1924 # callback.
1925 with self._lock:

File ~\anaconda3\Lib\site-packages\joblib\parallel.py:1847, in
Parallel._get_sequential_output(self, iterable)
1845 self.n_dispatched_batches += 1
1846 self.n_dispatched_tasks += 1
-> 1847 res = func(*args, **kwargs)
1848 self.n_completed_tasks += 1
1849 self.print_progress()

File ~\AppData\Roaming\Python\Python312\site-packages\sklearn\utils\
parallel.py:136, in _FuncWrapper.__call__(self, *args, **kwargs)
134 config = {}
135 with config_context(**config):
--> 136 return self.function(*args, **kwargs)

File ~\AppData\Roaming\Python\Python312\site-packages\sklearn\
model_selection\_validation.py:888, in _fit_and_score(estimator, X, y,
scorer, train, test, verbose, parameters, fit_params, score_params,
return_train_score, return_parameters, return_n_test_samples,
return_times, return_estimator, split_progress, candidate_progress,
error_score)
886 estimator.fit(X_train, **fit_params)
887 else:
--> 888 estimator.fit(X_train, y_train, **fit_params)
890 except Exception:
891 # Note fit time as time until error
892 fit_time = time.time() - start_time

File ~\AppData\Roaming\Python\Python312\site-packages\sklearn\
base.py:1473, in
_fit_context.<locals>.decorator.<locals>.wrapper(estimator, *args,
**kwargs)
1466 estimator._validate_params()
1468 with config_context(
1469 skip_parameter_validation=(
1470 prefer_skip_nested_validation or
global_skip_validation
1471 )
1472 ):
-> 1473 return fit_method(estimator, *args, **kwargs)

File ~\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:751, in
BaseMultilayerPerceptron.fit(self, X, y)
733 @_fit_context(prefer_skip_nested_validation=True)
734 def fit(self, X, y):
735 """Fit the model to data matrix X and target(s) y.
736
737 Parameters
(...)
749 Returns a trained MLP model.
750 """
--> 751 return self._fit(X, y, incremental=False)

File ~\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:488, in
BaseMultilayerPerceptron._fit(self, X, y, incremental)
486 # Run the LBFGS solver
487 elif self.solver == "lbfgs":
--> 488 self._fit_lbfgs(
489 X, y, activations, deltas, coef_grads,
intercept_grads, layer_units
490 )
492 # validate parameter weights
493 weights = chain(self.coefs_, self.intercepts_)

File ~\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:532, in
BaseMultilayerPerceptron._fit_lbfgs(self, X, y, activations, deltas,
coef_grads, intercept_grads, layer_units)
529 else:
530 iprint = -1
--> 532 opt_res = scipy.optimize.minimize(
533 self._loss_grad_lbfgs,
534 packed_coef_inter,
535 method="L-BFGS-B",
536 jac=True,
537 options={
538 "maxfun": self.max_fun,
539 "maxiter": self.max_iter,
540 "iprint": iprint,
541 "gtol": self.tol,
542 },
543 args=(X, y, activations, deltas, coef_grads,
intercept_grads),
544 )
545 self.n_iter_ = _check_optimize_result("lbfgs", opt_res,
self.max_iter)
546 self.loss_ = opt_res.fun

File ~\AppData\Roaming\Python\Python312\site-packages\scipy\optimize\
_minimize.py:731, in minimize(fun, x0, args, method, jac, hess, hessp,
bounds, constraints, tol, callback, options)
728 res = _minimize_newtoncg(fun, x0, args, jac, hess, hessp,
callback,
729 **options)
730 elif meth == 'l-bfgs-b':
--> 731 res = _minimize_lbfgsb(fun, x0, args, jac, bounds,
732 callback=callback, **options)
733 elif meth == 'tnc':
734 res = _minimize_tnc(fun, x0, args, jac, bounds,
callback=callback,
735 **options)

File ~\AppData\Roaming\Python\Python312\site-packages\scipy\optimize\
_lbfgsb_py.py:407, in _minimize_lbfgsb(fun, x0, args, jac, bounds,
disp, maxcor, ftol, gtol, eps, maxfun, maxiter, iprint, callback,
maxls, finite_diff_rel_step, **unknown_options)
401 task_str = task.tobytes()
402 if task_str.startswith(b'FG'):
403 # The minimization routine wants f and g at the current x.
404 # Note that interruptions due to maxfun are postponed
405 # until the completion of the current minimization
iteration.
406 # Overwrite f and g:
--> 407 f, g = func_and_grad(x)
408 elif task_str.startswith(b'NEW_X'):
 409 # new iteration
410 n_iterations += 1

File ~\AppData\Roaming\Python\Python312\site-packages\scipy\optimize\
_differentiable_functions.py:343, in ScalarFunction.fun_and_grad(self,
x)
341 if not np.array_equal(x, self.x):
342 self._update_x(x)
--> 343 self._update_fun()
344 self._update_grad()
345 return self.f, self.g

File ~\AppData\Roaming\Python\Python312\site-packages\scipy\optimize\
_differentiable_functions.py:294, in ScalarFunction._update_fun(self)
292 def _update_fun(self):
293 if not self.f_updated:
--> 294 fx = self._wrapped_fun(self.x)
295 if fx < self._lowest_f:
296 self._lowest_x = self.x

File ~\AppData\Roaming\Python\Python312\site-packages\scipy\optimize\
_differentiable_functions.py:20, in _wrapper_fun.<locals>.wrapped(x)
16 ncalls[0] += 1
17 # Send a copy because the user may overwrite it.
18 # Overwriting results in undefined behaviour because
19 # fun(self.x) will change self.x, with the two no longer
linked.
---> 20 fx = fun(np.copy(x), *args)
21 # Make sure the function returns a true scalar
22 if not np.isscalar(fx):

File ~\AppData\Roaming\Python\Python312\site-packages\scipy\optimize\
_optimize.py:79, in MemoizeJac.__call__(self, x, *args)
77 def __call__(self, x, *args):
78 """ returns the function value """
---> 79 self._compute_if_needed(x, *args)
80 return self._value

File ~\AppData\Roaming\Python\Python312\site-packages\scipy\optimize\
_optimize.py:73, in MemoizeJac._compute_if_needed(self, x, *args)
71 if not np.all(x == self.x) or self._value is None or self.jac
is None:
72 self.x = np.asarray(x).copy()
---> 73 fg = self.fun(x, *args)
74 self.jac = fg[1]
75 self._value = fg[0]

File ~\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:281, in
BaseMultilayerPerceptron._loss_grad_lbfgs(self, packed_coef_inter, X,
y, activations, deltas, coef_grads, intercept_grads)
240 """Compute the MLP loss function and its corresponding
derivatives
241 with respect to the different parameters given in the
initialization.
242
(...)
278 grad : array-like, shape (number of nodes of all layers,)
279 """
280 self._unpack(packed_coef_inter)
--> 281 loss, coef_grads, intercept_grads = self._backprop(
282 X, y, activations, deltas, coef_grads, intercept_grads
283 )
284 grad = _pack(coef_grads, intercept_grads)
285 return loss, grad

File ~\AppData\Roaming\Python\Python312\site-packages\sklearn\
neural_network\_multilayer_perceptron.py:357, in
BaseMultilayerPerceptron._backprop(self, X, y, activations, deltas,
coef_grads, intercept_grads)
355 # Iterate over the hidden layers
356 for i in range(self.n_layers_ - 2, 0, -1):
--> 357 deltas[i - 1] = safe_sparse_dot(deltas[i],
self.coefs_[i].T)
358 inplace_derivative(activations[i], deltas[i - 1])
360 self._compute_loss_grad(
361 i - 1, n_samples, activations, deltas, coef_grads,
intercept_grads
362 )

File ~\AppData\Roaming\Python\Python312\site-packages\sklearn\utils\
extmath.py:208, in safe_sparse_dot(a, b, dense_output)
204 else:
205 ret = a @ b
207 if (
--> 208 sparse.issparse(a)
209 and sparse.issparse(b)
210 and dense_output
211 and hasattr(ret, "toarray")
212 ):
213 return ret.toarray()
214 return ret

File ~\AppData\Roaming\Python\Python312\site-packages\scipy\sparse\
_base.py:1335, in issparse(x)
1329 """A namespace class to separate sparray from spmatrix"""
1332 sparray.__doc__ = _spbase.__doc__
-> 1335 def issparse(x):
1336 """Is `x` of a sparse array or sparse matrix type?
1337
 1338 Parameters
(...)
1359 False
1360 """
1361 return isinstance(x, _spbase)

KeyboardInterrupt: