ParthNipunDave

print('Number of unique values --> ',data['BloodPressure'].nunique())
sns.displot(data['BloodPressure'])
sns.boxplot(data=data,y='BloodPressure')
sns.boxplot(data=data,x='Outcome',y='BloodPressure')

ParthNipunDave

print('Number of unique values --> ',data['Glucose'].nunique())
sns.displot(data['Glucose'])
sns.boxplot(data=data,y='Glucose')
sns.boxplot(data=data,x='Outcome',y='Glucose')

ParthNipunDave

print('Number of unique values --> ',data['Pregnancies'].nunique())
sns.displot(data['Pregnancies'])
sns.boxplot(data=data,y='Pregnancies')
sns.boxplot(data=data,x='Outcome',y='Pregnancies')

ParthNipunDave

data=pd.read_csv('../input/pima-indians-diabetes-database/diabetes.csv')
print(data)
print(data.describe())
print(data.info())
print('Number of duplicate values --> ',data.duplicated().sum())

ParthNipunDave

import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report, recall_score
from imblearn.over_sampling import SMOTE
from keras.layers import Dense,Dropout
from keras.models import Sequential

ParthNipunDave

history=model.fit(train_data,validation_data=valid_data,steps_per_epoch=len(train_data),epochs=10)

ParthNipunDave

model=ResNet50(input_shape=(255,255,3),include_top=False,weights='imagenet',classes=80)
for layer in model.layers:
    layer.trainable=False
model=Sequential()
model.add(ResNet50(include_top=False,weights='imagenet',pooling='max'))
model.add(Dense(80,activation='softmax'))
model.compile(optimizer=tf.keras.optimizers.SGD(lr=0.0001),loss='categorical_crossentropy',metrics=['acc'])
model.summary()

ParthNipunDave

data=ImageDataGenerator(validation_split=0.3,zoom_range=0.3,rescale=1./255,horizontal_flip=True)
train_data=data.flow_from_directory('../input/animals-detection-images-dataset/train',target_size=(255,255),subset='training',shuffle=True,batch_size=8)
valid_data=data.flow_from_directory('../input/animals-detection-images-dataset/train',target_size=(255,255),subset='validation',shuffle=True,batch_size=8)
batch_size=8

ParthNipunDave

from keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.applications import ResNet50
from tensorflow.python.keras.models import Sequential
from tensorflow.python.keras.layers import Dense, Flatten, GlobalAveragePooling2D
from tensorflow.keras.applications import ResNet50
import tensorflow as tf
import matplotlib.pyplot as plt

ParthNipunDave

plt.plot(resnet_history.history["loss"],label="train")
plt.plot(resnet_history.history["val_loss"],label="val")
plt.title("Training Loss and Validation Loss")
plt.legend()