tensorflow-practice

Common packages for data

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
import seaborn as sns

Tensorflow Practice

1. Data set loading and visualization
2. Data Preprocessing/transforming
3. Modeling using tf.nn (more basic) / tf.keras (advance and convenient API for modeling)
4. Performance Visualization
5. Model saving and reuse, reload

import tensorflow as tf
import tensorflow.keras as keras
# This one-hot convert words to  index number rather than binary form
from tensorflow.keras.preprocessing.text import one_hot
#tf.one_hot import text/ labels into binary 0,1 form without compression
from numba import cuda

# Check if GPU is enabled
print(cuda.gpus)

<Managed Device 0>, <Managed Device 1>

Basic Practise

1. tf.constant contain types of data. Operation like +, -, *, / , should be applied to data with same types only

ls = np.random.randint(0,100,50)

ls= tf.constant(ls)
x1= tf.constant(1)
x2= tf.constant(2)
x4= tf.constant(5)
x3 = x1+x2*x4
tf.print(x3,[x1,x2])
tf.print(tf.argsort(ls))
c = tf.argsort(ls)

11 [1, 2]
[32 24 27 ... 20 40 49]

Practice with Text+Numeric type data: titanic data

TRAIN_DATA_URL = "https://storage.googleapis.com/tf-datasets/titanic/train.csv"
TEST_DATA_URL = "https://storage.googleapis.com/tf-datasets/titanic/eval.csv"

# The first param in get_file: the name of dataset to save
# The second param: url to the dataset 
trainset_path = keras.utils.get_file('titanic_train.csv', TRAIN_DATA_URL)
testset_path = keras.utils.get_file('titanic_test.csv', TEST_DATA_URL)
trainset_path,  testset_path

Downloading data from https://storage.googleapis.com/tf-datasets/titanic/train.csv
32768/30874 [===============================] - 0s 0us/step
Downloading data from https://storage.googleapis.com/tf-datasets/titanic/eval.csv
16384/13049 [=====================================] - 0s 0us/step





('/home/wenkanw/.keras/datasets/titanic_train.csv',
 '/home/wenkanw/.keras/datasets/titanic_test.csv')

# Load CSV file with pandas
trainset = pd.read_csv(trainset_path)
testset = pd.read_csv(testset_path)

trainset.head()

	survived	sex	age	n_siblings_spouses	parch	fare	class	deck	embark_town	alone
0	0	male	22.0	1	0	7.2500	Third	unknown	Southampton	n
1	1	female	38.0	1	0	71.2833	First	C	Cherbourg	n
2	1	female	26.0	0	0	7.9250	Third	unknown	Southampton	y
3	1	female	35.0	1	0	53.1000	First	C	Southampton	n
4	0	male	28.0	0	0	8.4583	Third	unknown	Queenstown	y

trainset.groupby('sex').head()

	survived	sex	age	n_siblings_spouses	parch	fare	class	deck	embark_town	alone
0	0	male	22.0	1	0	7.2500	Third	unknown	Southampton	n
1	1	female	38.0	1	0	71.2833	First	C	Cherbourg	n
2	1	female	26.0	0	0	7.9250	Third	unknown	Southampton	y
3	1	female	35.0	1	0	53.1000	First	C	Southampton	n
4	0	male	28.0	0	0	8.4583	Third	unknown	Queenstown	y
5	0	male	2.0	3	1	21.0750	Third	unknown	Southampton	n
6	1	female	27.0	0	2	11.1333	Third	unknown	Southampton	n
7	1	female	14.0	1	0	30.0708	Second	unknown	Cherbourg	n
9	0	male	20.0	0	0	8.0500	Third	unknown	Southampton	y
10	0	male	39.0	1	5	31.2750	Third	unknown	Southampton	n