Browsing Tag

python

b14
Deep Learning, Python,

Basic Image Recognition with Built-in Models in Keras

by admin-postMarch 13, 2018no comment

In this blog post we are going to look at Image Recognition with built-in models available in Keras. The notebook can be also viewed on Github.

There are various pre-trained models available in Keras. The weights for these models are trained on a subset of ImageNet dataset. ImageNet is an image dataset containing millions of images with each image described in words. The models are trained on a dataset of 1000 types of common objects (the list of 1000 categories). This dataset is used during The ImageNet Large Scale Visual Recognition Challenge (ILSVRC).

The models for image classification available in Keras are listed below:

  • Xception
  • VGG16
  • VGG19
  • ResNet50
  • InceptionV3
  • InceptionResNetV2
  • MobileNet
  • DenseNet
  • NASNet

Once the model is instantiated, the weights are automatically downloaded to ~/.keras/models/ folder. We will be implementing ResNet50 (50 Layer Residual Network – further reading: Deep Residual Learning for Image Recognition) in the example below. The file containing weights for ResNet50 is about 100MB.

The versions

In this example I am using Keras v.2.1.4 and TensorFlow v.1.5.0 with GPU (using NVIDIA CUDA).

 

Read more

b13
Deep Learning, Machine Learning, Python,

Basic Example of a Neural Network with TensorFlow and Keras

by admin-postMarch 6, 2018no comment

This blog post covers basic example of a Neural Network, using TensorFlow and Keras in Python. The notebook can be also viewed on Github.

TensorFlow and Keras

TensorFlow was developed at Google to use internally for machine learning tasks, and applied to the applications like speech recognition, Search, Gmail, etc. It was made public in 2015 as an open source application. The library is in C++, used with Python API. TensorFlow can be used for various problems like image recognition, language processing, implementation in self-driving cars, etc. There are various alternatives available to TensorFlow such as Theano, and Torch.

We are going to use Keras in this notebook, with Tensorflow as a backend engine. Keras is a high-level wrapper, which can be used both with TensorFlow and Theano. It simplifies common operations. The code is similar to scikit-learn, making it easier to get used to it, while in the background TensorFlow or Theano is used for processing.

The data

In this example we will be looking at MNIST database (a subset of a larger set by National Institute of Standards and Technology). This is a classic dataset containing 60000 training images, 10000 test images, and corresponding training and test labels. The images are handwritten digits, in the shape of 28 x 28 pixels, and divided into 10 categories (from 0 to 9).

The versions

In this example I am using Keras v.2.1.4 and TensorFlow v.1.5.0 with GPU (using NVIDIA CUDA). Running examples on a GPU can speed up the training process.

In [1]:
# To avoid warnings
import warnings
warnings.filterwarnings('ignore')

# Importing keras and tensorflow, and printing the versions
import keras
print('Keras: {}'.format(keras.__version__))

import tensorflow as tf
print('TensorFlow: {}'.format(tf.__version__))

Using TensorFlow backend.

Keras: 2.1.4
TensorFlow: 1.5.0

Read more

b12
Python,

Pandas – Tips and Tricks – df.loc, df.iloc

by admin-postFebruary 27, 2018no comment

This notebook is a part of Pandas – Tips and Tricks mini-series, focusing on different aspects of pandas library in Python. In the below examples we will be looking at selecting the data by using .loc and .iloc methods. The notebook is also available on GitHub.

.loc: is primarily label based indexing.

.iloc: is primarily integer position based indexing.

Previous blog posts on the topic: Data import with Python, using pandas DataFrame – Part 1

 

Let’s start by importing pandas and loading the data:

In [1]:
# Loading the library
import pandas as pd

# I am using the data from WHO as an example
df = pd.read_csv('Data/SuicBoth.csv')

# Checking the DataFrame shape
print(df.shape)

# Checking the imported data
df.head()

(183, 6)

Read more

b10
Python,

String, String Methods, and String Manipulation

by admin-postJanuary 30, 2018no comment

String is a collection of characters. Any character can be accessed by its index. The indexing of a string starts at 0 (or -1 if it’s indexed from the end). We can get the number of characters in a string by using built-in function len. Compared to the indexing, len is not zero based.

In [1]:
# Creating a string
text = 'Some collection of words'

# Assigning the number of characters in the given string to a variable
total_char = len(text)

# Printing the total number of characters
print('Number of characters = {}'.format(total_char))

Number of characters = 24

Read more

b9
Machine Learning, Python,

Machine Learning – Programming Exercise 2: Logistic Regression

by admin-postOctober 11, 2017no comment

Programming Exercise 2: Logistic Regression

The following blog post contains exercise solution for logistic regression assignment from the Machine Learning course by Andrew Ng. Also, this blog post is available as a jupyter notebook on GitHub.

In [1]:
# Standard imports. Importing seaborn for styling.
%matplotlib inline
import numpy as np
import matplotlib.pyplot as plt
import seaborn; seaborn.set_style('whitegrid')

Read more

b8
Machine Learning, Python,

k-NN Nearest Neighbor Classifier

by admin-postSeptember 30, 2017no comment

Nearest Neighbor Classification

k-Nearest Neighbors (k-NN) is one of the simplest machine learning algorithms. Predictions for the new data points are done by closest data points in the training data set. The algorithm compares the Euclidean distances from the point of interest to the other data points to determine which class it belongs to. We can define the k-amount of the closest data points for the algorithm calculations.

Lower k results in low bias / high variance. As k grows, the method becomes less flexible, and decision boundary close to linear. Higher k results in high bias / low variance.

Few links on the topic:

Also, this blog post is available as a jupyter notebook on GitHub.

Read more

b7
Machine Learning, Python,

Machine Learning – Programming Exercise 1: Linear Regression

by admin-postSeptember 21, 2017no comment

Programming Exercise 1: Linear Regression

I started working on the Machine Learning course by Andrew Ng. The following blog post contains exercise solution for linear regression using gradient descent algorithm. Also, this blog post is available as a jupyter notebook on GitHub.

This exercise was done using Numpy library functions. I also used scikit-learn library to demonstrate another way of linear regression plotting.

In [1]:
# Standard imports. Importing seaborn for styling.
%matplotlib inline
import numpy as np
import matplotlib.pyplot as plt
import seaborn; seaborn.set_style("whitegrid")

Read more

b4
Python,

Data visualization with Python and Matplotlib / Scatter Plot – Part 3

by admin-postJuly 9, 2017no comment

Let’s look at what else can be done with the data from Part 1. We start with the csv import mentioned in Part 2. Looking at the data we see that we have data available for 2010 and 2015 years, and we can analyze the change in suicide rates.

In [1]:
%matplotlib inline
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib as mpl
In [2]:
table = pd.read_excel('mergedData.xlsx')
table.head()
Out[2]:
Country 2015_s 2010_s 2015_p 2013_p 2010_p 2013_d suiAve suiPerDeath deaPerPop
0 Afghanistan 5.5 5.2 32526.6 30682.5 27962.2 7.7 5.35 0.694805 0.77
1 Albania 4.3 5.3 2896.7 2883.3 2901.9 9.4 4.80 0.510638 0.94
2 Algeria 3.1 3.4 39666.5 38186.1 36036.2 5.7 3.25 0.570175 0.57
3 Angola 20.5 20.7 25022.0 23448.2 21220.0 13.9 20.60 1.482014 1.39
4 Antigua and Barbuda 0.0 0.2 91.8 90.0 87.2 6.8 0.10 0.014706 0.68

Read more

b3
Python,

Data visualization with Python and Matplotlib – Part 2

by admin-postJuly 7, 2017no comment

In the previous chapter I described how to import the needed data to Pandas DataFrames, and how to manipulate DataFrame object. Now lets take a look on how we can visualize that data in a plot form. This is by no means a proper analysis of the suicide rates. It is a plotting example.
Below are the necessary imports. ‘%matplotlib inline’ is IPython-specific directive which displays matplotlib plots in notebook. It can be removed and plt.show() can be added to the end of the code to display the plot. We are also importing numpy, pandas, matplotlib.pyplot for plotting, and separately matplotlib to work on specific matplotlib functions if needed.

In [1]:
%matplotlib inline
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib as mpl

Next step is to import our data and assign it to DataFrame. We created that table in the previous example.

In [2]:
table = pd.read_excel('mergedData.xlsx')
table.head()
Out[2]:
Country 2015_s 2010_s 2015_p 2013_p 2010_p 2013_d suiAve suiPerDeath deaPerPop
0 Afghanistan 5.5 5.2 32526.6 30682.5 27962.2 7.7 5.35 0.694805 0.77
1 Albania 4.3 5.3 2896.7 2883.3 2901.9 9.4 4.80 0.510638 0.94
2 Algeria 3.1 3.4 39666.5 38186.1 36036.2 5.7 3.25 0.570175 0.57
3 Angola 20.5 20.7 25022.0 23448.2 21220.0 13.9 20.60 1.482014 1.39
4 Antigua and Barbuda 0.0 0.2 91.8 90.0 87.2 6.8 0.10 0.014706 0.68

 

Read more

b2
Python,

Data import with Python, using pandas DataFrame – Part 1

by admin-postJuly 6, 2017no comment

World Health Organization provides a wide range of data available for download in different formats.
The data is accessible through their website: http://www.who.int/gho/en/
In this example we will be working with Pandas DataFrame to organize the data. As an example I am going to work on suicide rates throughout the world.

In [1]:
import pandas as pd

By using ‘read_csv’ function, suicide crude rates (per 100,000 people) data is assigned to pandas object.

In [2]:
suicideData = pd.read_csv('SuicBoth.csv')
suicideData.head()
Out[2]:
Country Sex 2015 2010 2005 2000
0 Afghanistan Both sexes 5.5 5.2 5.4 4.8
1 Albania Both sexes 4.3 5.3 6.3 6.0
2 Algeria Both sexes 3.1 3.4 3.6 3.0
3 Angola Both sexes 20.5 20.7 20.0 18.4
4 Antigua and Barbuda Both sexes 0.0 0.2 1.6 2.3

Read more

Older Posts