Wednesday, January 24, 2024

ML: Image classification using Sklearn (RandomForest) 

  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
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
# https://www.kaggle.com/code/kkhandekar/image-classification-using-sklearn-randomforest/notebook

import numpy as np
import pandas as pd
import warnings
warnings.simplefilter('ignore')

import matplotlib.pyplot as plt
#%matplotlib inline
import os
import pprint
from collections import Counter
import joblib
from pprint import pprint
import cv2

from skimage.io import imread
from skimage.transform import resize
from skimage.transform import rescale


from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import RandomizedSearchCV, GridSearchCV

def resize_all(src, pklname, include, width=150, height=None):
    height=height if  height is not None else width

    data=dict()
    data['description']='resized ({0}*{1}) mini dog images in rgb'.format(int(width), int(height))
    data['label']=[]
    data['filename']=[]
    data['data']=[]

    pklname=f"{pklname}_{width}x{height}px.pkl"

    for subdir in os.listdir(src):
        if subdir in include:
            print(f"Reading images for {subdir} ...")
            current_path=os.path.join(src, subdir)
            for file in os.listdir(current_path):
                if file[-3:] in {'jpg', 'png'}:
                    im=imread(os.path.join(current_path, file))
                    im=resize(im, (width, height))
                    data['label'].append(subdir[:])
                    data['filename'].append(file)
                    data['data'].append(im)
        joblib.dump(data, pklname)




IMAGE_PATH='D:\A\Dat\AnoPyTest\kkk\MiniDogBreedData'
CLASSES=os.listdir(IMAGE_PATH)
BASE_NAME='mini_dog_breeds'
WIDTH=90

# Load & resize the images
resize_all(src=IMAGE_PATH, pklname=BASE_NAME, width=WIDTH, include=CLASSES)

data=joblib.load(f'{BASE_NAME}_{WIDTH}x{WIDTH}px.pkl')

print('number of samples: ', len(data['data']))
print('keys: ', list(data.keys()))
print('description: ', data['description'])
print('image shape: ', data['data'][0].shape)
print('labels: ', np.unique(data['label']))

print(Counter(data['label']))

labels=np.unique(data['label'])
# fig, axes=plt.subplot(1,  len(labels))
fig, axes = plt.subplots(1, len(labels))
fig.set_size_inches(15, 4)
fig.tight_layout()



for ax, label in zip(axes, labels):
    idx=data['label'].index(label)
    ax.imshow(data['data'][idx])
    #plt.show()
    ax.axis('off')
    ax.set_title(label)


x=np.array(data['data'])
y=np.array(data['label'])

SIZE=0.1
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=SIZE, shuffle=True, random_state=np.random.randint(1,50))

print(f"Training Size: {x_train.shape[0]}\n Validation Size: {x_test.shape[0]}")



x_train=x_train/255.0
x_test=x_test/255.0



nsamples, nx, ny, nrgb=x_train.shape
x_train2=x_train.reshape((nsamples, nx*ny*nrgb))


nsamples, nx, ny,nrgb=x_test.shape
x_test2=x_test.reshape((nsamples, nx*ny*nrgb))


rfc=RandomForestClassifier()
rfc.fit(x_train2, y_train)

y_pred=rfc.predict(x_test2)

from sklearn.metrics import accuracy_score
acc='{:.2%}'.format(accuracy_score(y_test, y_pred))
print(f"Accuracy for Random Forrest: {acc}")


n_estimators=[int(x) for x in np.linspace(start=200, stop=1000, num=3)]
criterion=['gini', 'entropy']
max_depth=[int(x) for x in np.linspace(10, 110, num=3)]
max_depth.append(None)


min_samples_split=[2, 5, 10]
min_samples_leaf=[1, 2, 4]

bootstrap=[True, False]

class_weight=['balanced', 'balanced_subsample', None]

param_grid={'n_estimators': n_estimators,
            'criterion': criterion,
            'max_depth': max_depth,
            'min_samples_split': min_samples_split,
            'min_samples_leaf': min_samples_leaf, 'bootstrap': bootstrap,
            'class_weight': class_weight}


pprint(param_grid)


rfc_t=RandomForestClassifier()

rf_random=RandomizedSearchCV(
    estimator=rfc_t,
    param_distributions=param_grid,
    n_iter=10,
    cv=3,
    verbose=0,
    random_state=42,
    n_jobs=-1
)


rf_random.fit(x_train2, y_train)
rf_random.best_params_


rfc=RandomForestClassifier()
rfc.fit(x_train2, y_train)
y_pred=rfc.predict(x_test2)

# accuracy score
acc = '{:.1%}'.format(accuracy_score(y_test, y_pred))
print(f"Accuracy for Random Forrest: {acc}")
Posted by at
Labels:

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)