jovianlin

def normalize(train, test):
    mean, std = train.mean(), test.std()
    train = (train - mean) / std
    test = (test - mean) / std
    return train, test

jovianlin

# Train the logistic rgeression classifier
clf = sklearn.linear_model.LogisticRegressionCV()
clf.fit(X, y)
 
# Plot the decision boundary
plot_decision_boundary(lambda x: clf.predict(x))
plt.title("Logistic Regression")

jovianlin

"""
### Problem Statement ###
Let's say you have a square matrix which consists of cosine similarities (values between 0 and 1).
This square matrix can be of any size. 
You want to get clusters which maximize the values between elemnts in the cluster.
For example, for the following matrix:

  |  A  |  B  |  C  |  D
A | 1.0 | 0.1 | 0.6 |  0.4
B | 0.1 | 1.0 | 0.1 |  0.2

jovianlin

def fix_encoding(some_str):
    return ''.join([c for c in some_str if 0x20 <= ord(c) <= 0x78])

    

jovianlin

# ===================================================================================
# Many thanks to:
# https://uoa-eresearch.github.io/eresearch-cookbook/recipe/2014/11/20/conda/
#
# More info:
# https://www.continuum.io/blog/developer-blog/python-packages-and-environments-conda
# https://conda-forge.github.io/#about
# ===================================================================================

# conda info --env

jovianlin

from functools import lru_cache

@lru_cache(maxsize=100)
def fibonacci(n):
  # Check that the input is a positive integer
  if type(n) != int:
    raise TypeError("n must be a positive int")
  if n < 1:
    raise ValueError("n must be a positive int")
    

jovianlin

def foo(s):
	if len(s) <= 0:
		return None
	else:
		output, curr_char, curr_count = '', '', 0
		for idx in range(0, len(s)):
			if s[idx] == curr_char:
				curr_count += 1
			else:
				output += curr_char + str(curr_count) if curr_count > 0 else curr_char

jovianlin

from sklearn.linear_model import SGDRegressor
 
# https://adventuresindatascience.wordpress.com/2014/12/30/minibatch-learning-for-large-scale-data-using-scikit-learn/
  
def iter_minibatches(chunksize, numtrainingpoints):
    # Provide chunks one by one
    chunkstartmarker = 0
    while chunkstartmarker < numtrainingpoints:
        chunkrows = range(chunkstartmarker,chunkstartmarker+chunksize)
        X_chunk, y_chunk = getrows(chunkrows)

jovianlin

# -*- coding: utf-8 -*-

from afinn import Afinn
import spacy
import re


class TargetedSentimentAnalysis(object):
	def __init__(self):
		self.afinn = Afinn(emoticons=True)

jovianlin

import argparse
import sys

def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('--x', type=float, default=1.0,
                        help='What is the first number?')
    parser.add_argument('--y', type=float, default=1.0,
                        help='What is the second number?')
    parser.add_argument('--operation', type=str, default='add',