TENSORFLOW LAB:

1. Basics of tensorflow
2. Load a dataset using tensorflow
3. Build a machine learning model
4. Detecting spam messages using tensorflow
5. Image classification using tensorflow
6. Optical character recognition using tensorflow
7. Object detection using tensorflow
8. Face recognition using tensorflow

CO:

Students will be able to

 install and set up TensorFlow in various environments.

 import datasets from various sources (CSV, images, text) using TensorFlow.
 Construct the machine learning models using the tf.keras API.
 build and train models specifically designed for spam detection,image classification tasks ,OCR tasks,
detecting objects within images, face recognition tasks.
 1. Basics of tensorflow
In[1]:

import tensorflow as tf

# Check if eager execution is enabled

print(tf.executing_eagerly())
true
In[2]:

import tensorflow as tf

# Define a simple computation

a = tf.constant(2)
b = tf.constant(3)
c = tf.add(a, b)

# Directly execute the computation

result = c.numpy()

print("Result:", result)
5
In[3]:

import tensorflow as tf

# Create a TensorFlow session

with tf.compat.v1.Session() as sess:
# Your TensorFlow operations go here
pass
In[4]:

import tensorflow as tf

# Enable eager execution (enabled by default in TensorFlow 2.x)

tf.compat.v1.disable_eager_execution()

# Define a simple computation

a = tf.constant(2)
b = tf.constant(3)
c = tf.add(a, b)

# Create a TensorFlow session

with tf.compat.v1.Session() as sess:
# Run the computation graph by executing the session
result = sess.run(c)
print("Result:", result)
Result: 5
In[5]:

# importing tensorflow
import tensorflow as tf

# creating nodes in computation graph

node1 = tf.constant(3, dtype=tf.int32)
node2 = tf.constant(5, dtype=tf.int32)
node3 = tf.add(node1, node2)

# create tensorflow session object

sess = tf.compat.v1.Session()

# evaluating node3 and printing the result

print("sum of node1 and node2 is :",sess.run(node3))
# closing the session
sess.close()
Sum of node1 and node2 is : 8
In[6]:
tf.compat.v1.Session(
target='', graph=None, config=None
)
<tensorflow.python.client.session.Session at 0x1bc3daf37d0>
In[7]:

tf.compat.v1.disable_eager_execution() # need to disable eager in TF2.x

# Build a graph.
a = tf.constant(5.0)
b = tf.constant(6.0)
c=a*b

# Launch the graph in a session.

sess = tf.compat.v1.Session()

# Evaluate the tensor `c`.

print(sess.run(c)) # prints 30.0
30.0
In[8]:

# Launch the graph in a session that allows soft device placement and
# logs the placement decisions.
sess = tf.compat.v1.Session(config=tf.compat.v1.ConfigProto(
allow_soft_placement=True,
log_device_placement=True))
Device mapping: no known devices.
In[9]:

devices = sess.list_devices()
for d in devices:
print(d.name)
/job:localhost/replica:0/task:0/device:CPU:0
In[10]:

import tensorflow as tf

# Assuming you have a list of sentences called 'text_corpus'

text_corpus = ["This is a sample sentence.", "Another sentence for example."]

# Create a Tokenizer object

tokenizer = tf.keras.preprocessing.text.Tokenizer()

# Fit the Tokenizer on your text corpus to build the vocabulary

tokenizer.fit_on_texts(text_corpus)

# Get the vocab_size (total number of unique words in the corpus)

vocab_size = len(tokenizer.word_index) + 1 # Adding 1 for the reserved index 0

print("Vocabulary Size:", vocab_size)

Vocabulary Size: 9
In[11]:

import tensorflow as tf

vocab_size = 10000 # Example vocabulary size

embedding_dim = 100 # Example embedding dimension
max_sequence_length = 100 # Example maximum sequence length

model = tf.keras.Sequential([
tf.keras.layers.Embedding(input_dim=vocab_size, output_dim=embedding_dim,
input_length=max_sequence_length),
# Other layers of your model...
])
In[12]:

import tensorflow as tf

# Check TensorFlow version

print(tf.__version__)

# Simple TensorFlow program

a = tf.constant(2)
b = tf.constant(3)
c=a+b

# Start a TensorFlow session and run the computation

with tf.compat.v1.Session() as sess:
result = sess.run(c)
print("Result:", result)
2.12.0 Result: 5
2) Load a dataset
In[1]:

Pip install tensorflow_datasets

Requirement already satisfied: tensorflow_datasets in c:\users\91970\appdata\local\

programs\python\python311\lib\site-packages (4.9.2)
Requirement already satisfied: absl-py in c:\users\91970\appdata\local\programs\
python\python311\lib\site-packages (from tensorflow_datasets) (1.4.0)
Requirement already satisfied: array-record in c:\users\91970\appdata\local\
programs\python\python311\lib\site-packages (from tensorflow_datasets) (0.4.0)
Requirement already satisfied: click in c:\users\91970\appdata\local\programs\
python\python311\lib\site-packages (from tensorflow_datasets) (8.1.3)
Requirement already satisfied: dm-tree in c:\users\91970\appdata\local\programs\
python\python311\lib\site-packages (from tensorflow_datasets) (0.1.8)
Requirement already satisfied: etils[enp,epath]>=0.9.0 in c:\users\91970\appdata\
local\programs\python\python311\lib\site-packages (from tensorflow_datasets) (1.3.0)
Requirement already satisfied: numpy in c:\users\91970\appdata\local\programs\
python\python311\lib\site-packages (from tensorflow_datasets) (1.23.5)
Requirement already satisfied: promise in c:\users\91970\appdata\local\programs\
python\python311\lib\site-packages (from tensorflow_datasets) (2.3)
Requirement already satisfied: protobuf>=3.20 in c:\users\91970\appdata\local\
programs\python\python311\lib\site-packages (from tensorflow_datasets) (4.23.3)
Requirement already satisfied: psutil in c:\users\91970\appdata\local\programs\
python\python311\lib\site-packages (from tensorflow_datasets) (5.9.5)
Requirement already satisfied: requests>=2.19.0 in c:\users\91970\appdata\local\
programs\python\python311\lib\site-packages (from tensorflow_datasets) (2.31.0)
Requirement already satisfied: tensorflow-metadata in c:\users\91970\appdata\local\
programs\python\python311\lib\site-packages (from tensorflow_datasets) (1.13.1)
Requirement already satisfied: termcolor in c:\users\91970\appdata\local\programs\
python\python311\lib\site-packages (from tensorflow_datasets) (2.3.0)
Requirement already satisfied: toml in c:\users\91970\appdata\local\programs\python\
python311\lib\site-packages (from tensorflow_datasets) (0.10.2)
Requirement already satisfied: tqdm in c:\users\91970\appdata\local\programs\python\
python311\lib\site-packages (from tensorflow_datasets) (4.65.0)
Requirement already satisfied: wrapt in c:\users\91970\appdata\local\programs\
python\python311\lib\site-packages (from tensorflow_datasets) (1.14.1)
Requirement already satisfied: importlib_resources in c:\users\91970\appdata\local\
programs\python\python311\lib\site-packages (from etils[enp,epath]>=0.9.0-
>tensorflow_datasets) (5.12.0)
Requirement already satisfied: typing_extensions in c:\users\91970\appdata\local\
programs\python\python311\lib\site-packages (from etils[enp,epath]>=0.9.0-
>tensorflow_datasets) (4.6.3)
Requirement already satisfied: zipp in c:\users\91970\appdata\local\programs\python\
python311\lib\site-packages (from etils[enp,epath]>=0.9.0->tensorflow_datasets)
(3.15.0)
Requirement already satisfied: charset-normalizer<4,>=2 in c:\users\91970\appdata\
local\programs\python\python311\lib\site-packages (from requests>=2.19.0-
>tensorflow_datasets) (3.1.0)
Requirement already satisfied: idna<4,>=2.5 in c:\users\91970\appdata\local\
programs\python\python311\lib\site-packages (from requests>=2.19.0-
>tensorflow_datasets) (3.4)
Requirement already satisfied: urllib3<3,>=1.21.1 in c:\users\91970\appdata\local\
programs\python\python311\lib\site-packages (from requests>=2.19.0-
>tensorflow_datasets) (1.26.16)
Requirement already satisfied: certifi>=2017.4.17 in c:\users\91970\appdata\local\
programs\python\python311\lib\site-packages (from requests>=2.19.0-
>tensorflow_datasets) (2023.5.7)
Requirement already satisfied: colorama in c:\users\91970\appdata\local\programs\
python\python311\lib\site-packages (from click->tensorflow_datasets) (0.4.6)
Requirement already satisfied: six in c:\users\91970\appdata\local\programs\python\
python311\lib\site-packages (from promise->tensorflow_datasets) (1.16.0)
Requirement already satisfied: googleapis-common-protos<2,>=1.52.0 in c:\users\
91970\appdata\local\programs\python\python311\lib\site-packages (from tensorflow-
metadata->tensorflow_datasets) (1.59.1)
Note: you may need to restart the kernel to use updated packages.
In[2]:

import tensorflow as tf
import tensorflow_datasets as tfds
import pandas as pd
tfds.list_builders()
ds=tfds.load('mnist',split='train',shuffle_files=True)
assert isinstance(ds,tf.data.Dataset)
print(ds)
<_PrefetchDataset element_spec={'image': TensorSpec(shape=(28, 28, 1),
dtype=tf.uint8, name=None), 'label': TensorSpec(shape=(), dtype=tf.int64,
name=None)}>

3) Build a machine learning model

In[1]:

# Import necessary libraries

from sklearn.datasets import make_circles
import matplotlib.pyplot as plt

# Generate 2d classification dataset

X, y = make_circles(n_samples=200, shuffle=True,
noise=0.1, random_state=42)
# Plot the generated datasets
plt.scatter(X[:, 0], X[:, 1], c=y)
plt.show()

In[2]:

import matplotlib.pyplot as plt

from mpl_toolkits.mplot3d import Axes3D

def visualize_3d(X, y):

fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.scatter(X['x'], X['y'], X['z'], c=y)
plt.show()

# Now you can call the visualize_3d function

X1 = pd.DataFrame(X1, columns=['x', 'y', 'z'])
y1 = pd.Series(y1)
visualize_3d(X1, y1)
In[3]:

import matplotlib.pyplot as plt

import seaborn as sns
from sklearn.datasets import make_classification
import pandas as pd

# Generate synthetic data

X, y = make_classification(n_samples=10000, n_features=2, n_informative=2, n_redundant=0, n_repeated=0,
n_classes=2, n_clusters_per_class=1, class_sep=2, flip_y=0.2, weights=[0.5, 0.5], random_state=17)

f, (ax1, ax2) = plt.subplots(nrows=1, ncols=2, figsize=(20, 8))

# Use sns.scatterplot with the data parameter and column names for x and y
sns.scatterplot(data=pd.DataFrame({'X0': X[:, 0], 'X1': X[:, 1], 'y': y}), x='X0', y='X1', hue='y', ax=ax1)
ax1.set_title("No Noise")

# Continue with your code here...

# Create another scatterplot for the noisy data

sns.scatterplot(data=pd.DataFrame({'X0': X[:, 0], 'X1': X[:, 1], 'y': y}), x='X0', y='X1', hue='y', ax=ax2)
ax2.set_title("With Noise")

plt.show()

In[4]:

import matplotlib.pyplot as plt

from mpl_toolkits.mplot3d import Axes3D
import pandas as pd
import numpy as np
def visualize_3d(X, y):
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')

# Create a colormap for coloring the points based on 'y'

cmap = plt.get_cmap('viridis') # You can choose a different colormap

# Normalize 'y' values to use them as colors

norm = plt.Normalize(y.min(), y.max())

# Scatter plot with colors based on 'y'

sc = ax.scatter(X['x'], X['y'], X['z'], c=y, cmap=cmap, norm=norm)

# Add color bar for reference

cb = plt.colorbar(sc)
cb.set_label('Label Value')

plt.show()

# Example data (replace with your actual data)

X1 = pd.DataFrame({'x': np.random.rand(100), 'y': np.random.rand(100), 'z': np.random.rand(100)})
y1 = np.random.randint(0, 2, size=100)

# Create DataFrames
X = pd.DataFrame(X1, columns=['x', 'y', 'z'])
y = pd.Series(y1)

# Now you can call the visualize_3d function

visualize_3d(X, y)
4) Detecting spam usting Tensorflow.

→ Detecting spam messages wing Tensorflow on Kaggle typically involves some coding or Script execution,
→Kaggle es a Primarily competitions and to use Tensorflow or any other machine learning! a platform for datascience
and machine learning you generally need to write code or use pre-existing code scripts. 30- Prameute
However, you are looking for a more wer-friendly way to Perform spam detection without writing code, you can expore
kaggle's "Kernels feature, Kaggle kernels allocos you for Tun code scripts shared by others without writing code
yourself, as so long as some one has created and shared a Kernel for the specific task you want to accomplish.
→ Here are the woogle general steps to perform spam detection using TensorFlow on Kaggle: have a kaggle account,
Sign up fo
1. Login to kaggle: If you don't one your need an account to aready access kaggle's resources.
2. find a Dataset: Search for a Dataset on kaggle that contains text message abelled as spam or not spam Cham). you can
use kaggle's dataset Search feature to find relevant data sets.
3. Create a kaggle Notebook:
• Go to Kaggle and click on "Notebooks" in the top menu.
• click on "New Notebook" to create ar nelo Notebook.
• choose a python crufɣonment (e.g.., Tensorflow) for your Notebook.
4. Load and explore the Dataset In your kaggle notebook, you can use Python code to load and explore the datas
for example:
Python
import pandas as ed data = fd Yead. csv C'path_to-your- dataset.csv')
5. Data preprocessing:
- Preprocess the text data by clearing and to Renizing it. you may need to remove punctuation, convert text to lowercase,
and tokenize the tex words or subwords.
6 Data splitting:
-split your dataset into your training, validation and test sets. This is import -ant for Elarining and evaluating your
machine learning model.
7. Text vectorization:
convert the text data into numerical format wing techniques like TP-DDF (Term Requency- Inverse Document
Frequency) or woord embedding like word 2 Vec by Glove.
8. Build a spam Detection model!
Create a TensorFloco model for spam detection. you can use various architectures such as Recurrent Neural Network
(RNNs), convolution Neural Network
(CNNs) or Transformer Models. -ation metrics. Define the model layers, compile it, and set up evalu
9. Training:
•Train your Tensorflow model on the Training uting validation data to avoid overfitting. 10-Evaluation: data. Monitor
training performance
-Evaluate the model's performance on the test dataset. common metrics for text classification tasks include accuracy,
precision, recall, and fi-score
11. Turing and optimization:
-Experiment with different model architectures, hyper parameters, and preprocessing techniques to optimize your spam
detection model.
12. Deployment:
-If you want to use the ad trofined model for real-word Spam detection, you can deploy it as a web service or integrate it
into your application. Kaggle provid resources for deploying models, or you can explore other deployment platforms like
Flask or Tensorflow serving.
13. Share your work?
-If you've achieved good results, consider sharing your kaggle notebook with the community to help others learn and
improve their spam detection models.

KAGGLE DATASET LINK:

https://www.kaggle.com/code/akanksha496/spam-detection-using-tensorflow/input
In[1]:

import tensorflow as tf
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
In[2]:

data = pd.read_csv('C:/Users/91970/Documents/MAHE/OneDrive/Desktop/SPAM text message 20170820 -

Data.csv')
In[3]:

data.head()
Categor
Message
y

0 ham Go until jurong point, crazy.. Available only ...

1 ham Ok lar... Joking wif u oni...

2 spam Free entry in 2 a wkly comp to win FA Cup fina...

3 ham U dun say so early hor... U c already then say...

4 ham Nah I don't think he goes to usf, he lives aro..

In[4]:

data.groupby('Category').describe().T

In[5]:

import seaborn as sns

import matplotlib.pyplot as plt

plt.figure(figsize=(12, 14))
sns.countplot(data=data, x='Category')
plt.show()

In[6]:

ham_msg = data[data.Category =='ham']

spam_msg = data[data.Category=='spam']

In[7]:

#randomly taking data from ham_ msg

ham_msg=ham_msg.sample(n=len(spam_msg),random_state=42)

In[8]:

print(ham_msg.shape,spam_msg.shape)
(747, 2) (747, 2)

In[9]:

# Assuming you have two DataFrames, ham_msg and spam_msg

# Concatenate the DataFrames vertically

balanced_data = pd.concat([ham_msg, spam_msg]).reset_index(drop=True)

# Create the count plot

plt.figure(figsize=(8, 6))
sns.countplot(data=balanced_data, x='Category')
plt.title('Distribution of ham and spam email messages (after downsampling)')
plt.show()
In[10]:

balanced_data.head()

In[11]:

balanced_data['label']=balanced_data['Category'].map({'ham':0,'spam':1})
In[12]:

train_msg, test_msg, train_labels,

test_labels=train_test_split(balanced_data['Message'],balanced_data['label'],test_size=0.2,random_state=434)
In[13]:

vocab_size=500
oov_tok='<OOV>'
max_len=50

In[14]:

#preprocessing making tokens out of text

token=Tokenizer(num_words=vocab_size,oov_token=oov_tok)
token.fit_on_texts(train_msg)

In[15]:

word_index=token.word_index
word_index
{'<OOV>': 1,
'to': 2,
'you': 3,
'a': 4,
'i': 5,
'call': 6,
'the': 7,
'your': 8,
'u': 9,
'for': 10,
'2': 11,
'and': 12,
'is': 13,
'now': 14,
'free': 15,
'or': 16,
'in': 17,
'on': 18,
'have': 19,
'ur': 20,
'of': 21,
'txt': 22,
'4': 23,
'me': 24,
'are': 25,
'with': 26,
'from': 27,
'text': 28,
'this': 29,
'my': 30,
'get': 31,
'stop': 32,
'mobile': 33,
'just': 34,
'no': 35,
'it': 36,
'will': 37,
'reply': 38,
'only': 39,
'be': 40,
'that': 41,
'claim': 42,
'www': 43,
'not': 44,
'out': 45,
'do': 46,
'send': 47,
'new': 48,
'so': 49,
'our': 50,
'we': 51,
'but': 52,
'at': 53,
'prize': 54,
'can': 55,
'cash': 56,
'all': 57,
'if': 58,
"i'm": 59,
'who': 60,
'150p': 61,
'uk': 62,
'go': 63,
'1': 64,
'nokia': 65,
'please': 66,
'win': 67,
't': 68,
'tone': 69,
'won': 70,
'week': 71,
'com': 72,
'msg': 73,
'50': 74,
'was': 75,
'day': 76,
'up': 77,
'phone': 78,
'by': 79,
'been': 80,
'what': 81,
'want': 82,
'service': 83,
'know': 84,
'urgent': 85,
'lt': 86,
'gt': 87,
'contact': 88,
'when': 89,
'co': 90,
'has': 91,
'18': 92,
'16': 93,
'min': 94,
'message': 95,
'r': 96,
'customer': 97,
'good': 98,
'per': 99,
'how': 100,
'guaranteed': 101,
'time': 102,
'as': 103,
'love': 104,
'like': 105,
'then': 106,
'line': 107,
'c': 108,
'any': 109,
'cs': 110,
'number': 111,
'3': 112,
'find': 113,
'chat': 114,
'back': 115,
'got': 116,
'draw': 117,
'its': 118,
'am': 119,
'awarded': 120,
'ü': 121,
'camera': 122,
'today': 123,
'dont': 124,
"don't": 125,
'ok': 126,
'more': 127,
'every': 128,
'need': 129,
'sorry': 130,
'£1': 131,
'there': 132,
'£1000': 133,
'about': 134,
'mins': 135,
'wk': 136,
'had': 137,
'great': 138,
'hi': 139,
'receive': 140,
"i'll": 141,
'pls': 142,
'sms': 143,
'holiday': 144,
'po': 145,
'latest': 146,
'tell': 147,
'n': 148,
'rate': 149,
'yes': 150,
'see': 151,
'they': 152,
'video': 153,
'box': 154,
'hey': 155,
'come': 156,
'chance': 157,
'shows': 158,
'dear': 159,
'apply': 160,
'thanks': 161,
'award': 162,
'150ppm': 163,
'landline': 164,
'tones': 165,
'an': 166,
's': 167,
'code': 168,
'1st': 169,
'still': 170,
'live': 171,
'special': 172,
'network': 173,
'ringtone': 174,
'make': 175,
'give': 176,
'orange': 177,
'take': 178,
'e': 179,
'b': 180,
'selected': 181,
'collect': 182,
'next': 183,
'miss': 184,
'da': 185,
'weekly': 186,
'best': 187,
'cost': 188,
'500': 189,
'£100': 190,
'valid': 191,
'music': 192,
'mob': 193,
'10p': 194,
'play': 195,
'offer': 196,
'name': 197,
'over': 198,
'her': 199,
'entry': 200,
'hope': 201,
'life': 202,
'one': 203,
'8007': 204,
'national': 205,
'going': 206,
'last': 207,
'some': 208,
'home': 209,
"it's": 210,
'collection': 211,
'well': 212,
'he': 213,
'vouchers': 214,
'd': 215,
'000': 216,
'later': 217,
'think': 218,
'why': 219,
'real': 220,
'texts': 221,
'end': 222,
'oh': 223,
'where': 224,
'games': 225,
'club': 226,
'trying': 227,
'£500': 228,
'help': 229,
'work': 230,
'lor': 231,
'http': 232,
'tomorrow': 233,
'poly': 234,
'5': 235,
'should': 236,
'after': 237,
'delivery': 238,
'10': 239,
'86688': 240,
'happy': 241,
'join': 242,
'night': 243,
'todays': 244,
'price': 245,
'waiting': 246,
'someone': 247,
'sae': 248,
'word': 249,
'update': 250,
'morning': 251,
"c's": 252,
'im': 253,
'bonus': 254,
'keep': 255,
'land': 256,
'gift': 257,
'bt': 258,
'x': 259,
'g': 260,
'guess': 261,
'enjoy': 262,
'sent': 263,
'£2000': 264,
'speak': 265,
'opt': 266,
'she': 267,
'voucher': 268,
'dating': 269,
'6': 270,
'await': 271,
'double': 272,
'colour': 273,
'£3': 274,
'sexy': 275,
'operator': 276,
'£5000': 277,
'100': 278,
'services': 279,
'7': 280,
'friend': 281,
'first': 282,
'top': 283,
'12hrs': 284,
'xmas': 285,
'k': 286,
'750': 287,
'use': 288,
'yours': 289,
'here': 290,
'attempt': 291,
'which': 292,
'babe': 293,
'cos': 294,
'mobileupd8': 295,
'hot': 296,
'being': 297,
'let': 298,
'quiz': 299,
"can't": 300,
'08000930705': 301,
'account': 302,
'order': 303,
'private': 304,
'much': 305,
'soon': 306,
'content': 307,
'part': 308,
'£350': 309,
'half': 310,
'unsubscribe': 311,
'talk': 312,
'wat': 313,
'ltd': 314,
'fun': 315,
'tried': 316,
'way': 317,
'row': 318,
'friends': 319,
'could': 320,
'pic': 321,
'2nd': 322,
'days': 323,
'gud': 324,
'£250': 325,
'off': 326,
'doing': 327,
'hello': 328,
'ask': 329,
'camcorder': 330,
'charged': 331,
'meet': 332,
'yeah': 333,
'm': 334,
'worth': 335,
'too': 336,
'us': 337,
'congratulations': 338,
'wkly': 339,
'87066': 340,
'them': 341,
'reveal': 342,
'cant': 343,
'cool': 344,
'weekend': 345,
'rental': 346,
'try': 347,
'auction': 348,
'freemsg': 349,
'pounds': 350,
'mates': 351,
'suite342': 352,
'2lands': 353,
'did': 354,
'class': 355,
'month': 356,
'08000839402': 357,
'care': 358,
'phones': 359,
'amp': 360,
'statement': 361,
'points': 362,
'identifier': 363,
'expires': 364,
'final': 365,
'tv': 366,
'check': 367,
'wap': 368,
'really': 369,
'each': 370,
'wish': 371,
'secret': 372,
'info': 373,
'£2': 374,
'easy': 375,
'winner': 376,
'mobiles': 377,
'feel': 378,
'start': 379,
'nice': 380,
'sure': 381,
'date': 382,
'money': 383,
'pics': 384,
'xxx': 385,
'0800': 386,
'him': 387,
'year': 388,
'ringtones': 389,
'would': 390,
'custcare': 391,
'rates': 392,
'between': 393,
'looking': 394,
'thing': 395,
'were': 396,
'other': 397,
'his': 398,
'question': 399,
'2003': 400,
'800': 401,
'savamob': 402,
'offers': 403,
'place': 404,
'f': 405,
'eg': 406,
'late': 407,
'admirer': 408,
'thinks': 409,
'right': 410,
'reward': 411,
'net': 412,
'tc': 413,
'direct': 414,
'calls': 415,
'already': 416,
'valued': 417,
'important': 418,
'txts': 419,
'same': 420,
'say': 421,
'messages': 422,
'call2optout': 423,
'around': 424,
'shop': 425,
'anything': 426,
'buy': 427,
'caller': 428,
'03': 429,
'std': 430,
'again': 431,
'minutes': 432,
'un': 433,
'redeemed': 434,
'does': 435,
'charge': 436,
'pick': 437,
'numbers': 438,
'said': 439,
'anytime': 440,
'busy': 441,
'job': 442,
're': 443,
'gr8': 444,
'went': 445,
'shopping': 446,
'may': 447,
'meeting': 448,
'pobox': 449,
'things': 450,
'w1j6hl': 451,
'very': 452,
'lol': 453,
'also': 454,
'fancy': 455,
'ntt': 456,
'true': 457,
'player': 458,
'balance': 459,
'currently': 460,
'never': 461,
'thk': 462,
'asked': 463,
'sex': 464,
'game': 465,
'congrats': 466,
'either': 467,
'house': 468,
'ts': 469,
'complimentary': 470,
'charity': 471,
'missing': 472,
'many': 473,
'even': 474,
'yr': 475,
'sir': 476,
'look': 477,
'matches': 478,
'comp': 479,
'ipod': 480,
'having': 481,
'visit': 482,
'ac': 483,
'while': 484,
'04': 485,
'£150': 486,
'discount': 487,
'getzed': 488,
'long': 489,
'ldew': 490,
'luv': 491,
'ready': 492,
'weeks': 493,
'these': 494,
"that's": 495,
'ending': 496,
'wanna': 497,
'before': 498,
'inc': 499,
'must': 500,
'plus': 501,
'digital': 502,
'dogging': 503,
'11': 504,
'ldn': 505,
'down': 506,
'told': 507,
'always': 508,
'age': 509,
"i've": 510,
'hg': 511,
'age16': 512,
'post': 513,
'answer': 514,
'area': 515,
'08712460324': 516,
'terms': 517,
"t's": 518,
'england': 519,
'v': 520,
'87077': 521,
'ip4': 522,
'5we': 523,
'man': 524,
'guys': 525,
'id': 526,
'motorola': 527,
'ya': 528,
'saturday': 529,
'20p': 530,
'polys': 531,
'choose': 532,
'representative': 533,
'match': 534,
'details': 535,
'msgs': 536,
'credit': 537,
'xx': 538,
'00': 539,
'mind': 540,
'eat': 541,
'£800': 542,
'cd': 543,
'welcome': 544,
'away': 545,
"you're": 546,
'enough': 547,
'y': 548,
'little': 549,
'haha': 550,
'nyt': 551,
'specially': 552,
'£10': 553,
'enter': 554,
'getting': 555,
'pm': 556,
'txting': 557,
'big': 558,
'user': 559,
'lucky': 560,
'log': 561,
"there's": 562,
'into': 563,
'maybe': 564,
'150': 565,
'years': 566,
'coming': 567,
'£200': 568,
'store': 569,
'hmv': 570,
'del': 571,
'within': 572,
'correct': 573,
'dude': 574,
'den': 575,
'wan': 576,
'two': 577,
'wait': 578,
'made': 579,
'flag': 580,
'eve': 581,
'news': 582,
'bluetooth': 583,
'hear': 584,
'bx420': 585,
'50p': 586,
'sony': 587,
'sunshine': 588,
'0870': 589,
'called': 590,
'girl': 591,
'summer': 592,
'dream': 593,
'trip': 594,
'rcvd': 595,
'08718720201': 596,
'pa': 597,
'birthday': 598,
'freephone': 599,
'local': 600,
'office': 601,
'arrive': 602,
'bid': 603,
'girls': 604,
'bout': 605,
'85023': 606,
'pobox84': 607,
'2004': 608,
'06': 609,
'sleep': 610,
'wants': 611,
'tncs': 612,
'brings': 613,
'minute': 614,
'vodafone': 615,
'since': 616,
'information': 617,
'room': 618,
'08712300220': 619,
'standard': 620,
'credits': 621,
'flights': 622,
'biz': 623,
'tickets': 624,
'book': 625,
'sub': 626,
'luck': 627,
'3030': 628,
'no1': 629,
'invited': 630,
'onto': 631,
'fantastic': 632,
'awaiting': 633,
'access': 634,
'dad': 635,
'o2': 636,
'replying': 637,
'vary': 638,
'ill': 639,
'spree': 640,
'nothing': 641,
'address': 642,
'maximize': 643,
'until': 644,
'people': 645,
'sipix': 646,
'pc': 647,
'gay': 648,
'done': 649,
'costa': 650,
'sol': 651,
'sk38xh': 652,
'something': 653,
'pay': 654,
'hit': 655,
'bit': 656,
'calling': 657,
'few': 658,
'email': 659,
'20': 660,
'ans': 661,
'02': 662,
'thought': 663,
'yo': 664,
'zed': 665,
'bad': 666,
'pass': 667,
'150pm': 668,
'hour': 669,
'horny': 670,
'25p': 671,
'sp': 672,
'yet': 673,
'holder': 674,
'god': 675,
'1327': 676,
'croydon': 677,
'cr9': 678,
'5wb': 679,
'link': 680,
'ring': 681,
'fri': 682,
'reach': 683,
'logo': 684,
'leh': 685,
'arcade': 686,
'st': 687,
'cum': 688,
'till': 689,
'asap': 690,
'sky': 691,
'11mths': 692,
'partner': 693,
'wont': 694,
'3510i': 695,
'full': 696,
'dvd': 697,
'greet': 698,
'member': 699,
'singles': 700,
'frnd': 701,
'62468': 702,
'themob': 703,
'sport': 704,
'crazy': 705,
'princess': 706,
'voda': 707,
'quoting': 708,
'goto': 709,
'comuk': 710,
'extra': 711,
'hours': 712,
'computer': 713,
'picked': 714,
'2optout': 715,
'txtauction': 716,
'fine': 717,
'watching': 718,
'guy': 719,
'unsub': 720,
"we're": 721,
'tonight': 722,
'36504': 723,
"u've": 724,
'xchat': 725,
'following': 726,
'urawinner': 727,
'surprise': 728,
'than': 729,
'via': 730,
'supposed': 731,
'loan': 732,
'10am': 733,
'hurt': 734,
'stay': 735,
'pound': 736,
'contacted': 737,
'entered': 738,
'unlimited': 739,
'8': 740,
'cc': 741,
'28': 742,
'better': 743,
'loyalty': 744,
'anyway': 745,
'conditions': 746,
"uk's": 747,
'aight': 748,
'09050090044': 749,
'toclaim': 750,
'pobox334': 751,
'stockport': 752,
'cost£1': 753,
'max10mins': 754,
'okay': 755,
'1x150p': 756,
'ho': 757,
'optout': 758,
'linerental': 759,
'another': 760,
'online': 761,
'took': 762,
'announcement': 763,
'etc': 764,
'heart': 765,
'park': 766,
"won't": 767,
'subscription': 768,
'believe': 769,
'revealed': 770,
'show': 771,
'12': 772,
'starts': 773,
'82277': 774,
'80062': 775,
'fantasies': 776,
'08707509020': 777,
'close': 778,
'immediately': 779,
'leave': 780,
"what's": 781,
'takes': 782,
'car': 783,
'3g': 784,
'click': 785,
'stuff': 786,
'wid': 787,
'fantasy': 788,
'once': 789,
'though': 790,
'll': 791,
'bed': 792,
'remember': 793,
'card': 794,
'huh': 795,
'40gb': 796,
'entitled': 797,
'download': 798,
'83600': 799,
'fone': 800,
'original': 801,
'3gbp': 802,
'action': 803,
'ever': 804,
'300': 805,
'hoping': 806,
'break': 807,
"we'll": 808,
'reference': 809,
'red': 810,
'everyone': 811,
'gone': 812,
'wife': 813,
'24': 814,
'm263uz': 815,
'town': 816,
'adult': 817,
'tuition': 818,
'flower': 819,
'inviting': 820,
'eerie': 821,
'4u': 822,
'rply': 823,
'pobox36504w45wq': 824,
'selection': 825,
'440': 826,
'cds': 827,
'com1win150ppmx3age16': 828,
'evening': 829,
'lots': 830,
'2nite': 831,
"you've": 832,
'months': 833,
'sept': 834,
'king': 835,
'b4': 836,
'£400': 837,
'w1': 838,
'finish': 839,
'bath': 840,
'movie': 841,
'found': 842,
'boys': 843,
'vip': 844,
'jamster': 845,
'laid': 846,
'locations': 847,
'ec2a': 848,
'everything': 849,
'seems': 850,
'7pm': 851,
'dun': 852,
'w45wq': 853,
'norm150p': 854,
'sign': 855,
'msgrcvdhg': 856,
'review': 857,
'driving': 858,
'fixed': 859,
'85': 860,
'left': 861,
'87239': 862,
'flirt': 863,
'recd': 864,
'sell': 865,
'lar': 866,
'alert': 867,
'hurry': 868,
'bored': 869,
'87131': 870,
'sale': 871,
'refused': 872,
"'help'": 873,
'starting': 874,
'250': 875,
'questions': 876,
'9': 877,
'simple': 878,
'09061221066': 879,
'fromm': 880,
'60p': 881,
'says': 882,
'confirm': 883,
'early': 884,
'okie': 885,
'liao': 886,
'w': 887,
'quite': 888,
'wif': 889,
'jay': 890,
'missed': 891,
'cause': 892,
'official': 893,
'alright': 894,
'santa': 895,
'team': 896,
'second': 897,
'goes': 898,
'blue': 899,
'support': 900,
'person': 901,
'08715705022': 902,
'bahamas': 903,
'cheap': 904,
'lot': 905,
"god's": 906,
'cust': 907,
'problem': 908,
'listen': 909,
'choice': 910,
'tariffs': 911,
'86021': 912,
'porn': 913,
'wanted': 914,
'…': 915,
'oso': 916,
'mths': 917,
'ordered': 918,
'oredi': 919,
'came': 920,
'0': 921,
'08712405020': 922,
'pub': 923,
'comes': 924,
'£4': 925,
'polyphonic': 926,
'hl': 927,
'weekends': 928,
'yup': 929,
'leaving': 930,
'semester': 931,
'noe': 932,
'bloomberg': 933,
'due': 934,
'o': 935,
'wil': 936,
'q': 937,
'sending': 938,
'short': 939,
'30': 940,
'wen': 941,
'forwarded': 942,
'til': 943,
'videophones': 944,
'videochat': 945,
'java': 946,
'dload': 947,
'noline': 948,
'rentl': 949,
'children': 950,
'chikku': 951,
'cancel': 952,
'netcollex': 953,
'app': 954,
'working': 955,
'available': 956,
'2day': 957,
'calls£1': 958,
"haven't": 959,
'press': 960,
'smth': 961,
'ppm': 962,
'kick': 963,
'tel': 964,
'mid': 965,
'spook': 966,
'goin': 967,
'pg': 968,
 'ntwk': 969,
'08001950382': 970,
'tenerife': 971,
'£900': 972,
'8552': 973,
'textpod': 974,
'ha': 975,
'1000s': 976,
'80082': 977,
'valentines': 978,
'dnt': 979,
'forget': 980,
'0808': 981,
'145': 982,
'4742': 983,
'9am': 984,
'11pm': 985,
'pod': 986,
'beyond': 987,
'deliveredtomorrow': 988,
'whats': 989,
'80488': 990,
'together': 991,
'befor': 992,
'kind': 993,
'cheers': 994,
'th': 995,
'subs': 996,
'05': 997,
'train': 998,
'exciting': 999,
'84025': 1000,
...}
In[16]:

padding_type='post'
truncate_type='post'
Trainning_seq=token.texts_to_sequences(train_msg)
Trainning_pad=pad_sequences(Trainning_seq,maxlen=50,padding=padding_type,truncating=truncate_type)

In[17]:

import tensorflow as tf
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences

data = pd.read_csv('C:/Users/91970/Documents/MAHE/OneDrive/Desktop/SPAM text message 20170820 -

Data.csv')

data.head()

data.groupby('Category').describe().T

import seaborn as sns

import matplotlib.pyplot as plt

plt.figure(figsize=(12, 14))
sns.countplot(data=data, x='Category')
plt.show()
6)Image classification using tensorflow
In[1]:
import tensorflow as tf
# Helper libraries
import numpy as np
import matplotlib.pyplot as plt

In[2]:
fashion_mnist = tf.keras.datasets.fashion_mnist
(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()

Output:
Downloading data from
https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-labels-idx1-
ubyte.gz
29515/29515 [==============================] - 0s 4us/step
Downloading data from
https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-images-idx3-
ubyte.gz
26421880/26421880 [==============================] - 23s 1us/step
Downloading data from
https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-labels-idx1-
ubyte.gz
5148/5148 [==============================] - 0s 0s/step
Downloading data from
https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-images-idx3-
ubyte.gz
4422102/4422102 [==============================] - 2s 1us/step

In[3]:
class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',
'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']
In[4]:
train_images.shape
ouput:
(60000, 28, 28)

In[5]:
len(train_labels)
output:
60000

In[6]:
train_labels
output:
array([9, 0, 0, ..., 3, 0, 5], dtype=uint8)
In[7]:
len(test_labels)
output:
10000

In[8]:
plt.figure()
plt.imshow(train_images[0])
plt.colorbar()
plt.grid(False)
plt.show()
output:
 \
In[9]:
train_images = train_images / 255.0
test_images = test_images / 255.0

In[10]:
plt.figure(figsize=(10,10))
for i in range(25):
plt.subplot(5,5,i+1)
plt.xticks([])
plt.yticks([])
plt.grid(False)
plt.imshow(train_images[i], cmap=plt.cm.binary)
plt.xlabel(class_names[train_labels[i]])
plt.show()
output:
7)FACE RECOGNITION USING TENSORFLOW
KAGGLE DATASET
https://www.kaggle.com/code/yk7283/facial-recognition-with-deep-learning/input
In[1]:
import tensorflow as tf
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
In[2]:
import numpy as np
# Replace 'YourUsername' with your actual username
file_path = r'C:/Users/91970/Documents/MAHE/OneDrive/Desktop/ORL_faces.npz'
data = np.load(file_path)

In[3]:
data_img= pd.DataFrame.from_dict({item: data[item] for item in data.files}, orient='index')
data_img

In[4]:
# Normalizing training data
X_train = np.array(data['trainX'],dtype='float32')/255
X_train

Output:

In[5]:
X_train.shape
Output:
(240, 10304)
In[6]:
# Normalizing testing data
X_test = np.array(data['testX'],dtype='float32')/255
X_test

In[7]:
X_test.shape
Output:
(160, 10304)

In[8]:
y_train= np.array(data['trainY'])
y_test= np.array(data['testY'])

In[9]:
print('Training dataset X_train, has', X_train.shape[0], 'rows and', X_train.shape[1], 'columns')
print('Testing dataset X_test, has', X_test.shape[0], 'rows and', X_test.shape[1], 'columns')
output:
Training dataset X_train, has 240 rows and 10304 columns
Testing dataset X_test, has 160 rows and 10304 columns

In[10]:
img_rows=112
img_cols=92
batch_size=512
img_shape=(img_rows, img_cols, 1)

In[11]:
X_train.shape
Output:
(240, 10304)

In[12]:
X_train.dtype
Ouput:
dtype('float32')

In[13]:
X_test.shape
Output:
(160, 10304)