vb100

""" Zoopla scraping project """

# Import libraries
import requests, re, os
import pandas as pd
from bs4 import BeautifulSoup

""" Generate the list of URLs : Start"""
def generateURLs(pages):
    listURLs = []

vb100

# 01 Calculate ECDF for Zoopla distribution model
def ecdf(data):
    """Compute ECDF for a one-dimensional array of measurements."""

    # Number of data points: n
    n = len(data)

    # x-data for the ECDF: x
    x = np.sort(data)

vb100

# Plot the ECDF
_ = plt.plot(x_vers, y_vers, '.')
plt.margins(0.02)
_ = plt.xlabel('petal length (cm)')
_ = plt.ylabel('ECDF')

# Overlay percentiles as red diamonds.
_ = plt.plot(ptiles_vers, percentiles/100, marker='D', color='red',
         linestyle='none')

vb100

def pearson_r(x, y):
    """Compute Pearson correlation coefficient between two arrays."""
    # Compute correlation matrix: corr_mat
    corr_mat = np.corrcoef(x, y)

    # Return entry [0,1]
    return corr_mat[0,1]

# Compute Pearson correlation coefficient for I. versicolor: r
r = pearson_r(versicolor_petal_length, versicolor_petal_width)

vb100

# Draw 10,000 samples out of Poisson distribution: samples_poisson
samples_poisson = np.random.poisson(10, size = 10000)

# Print the mean and standard deviation
print('Poisson:     ', np.mean(samples_poisson),
                       np.std(samples_poisson))

# Specify values of n and p to consider for Binomial: n, p
n = [20, 100, 1000]
p = [0.5, 0.1, 0.01]

vb100

# Import Table
from sqlalchemy import Table

# Reflect census table from the engine: census
census = Table('census', metadata, autoload=True, autoload_with=engine)

# Print census table metadata
print(repr(census))

vb100

# Reflect the census table from the engine: census
census = Table('census', metadata, autoload=True, autoload_with=engine)

# Print the column names
print(census.columns.keys())

# Print full table metadata
print(repr(metadata.tables['census']))

vb100

# Build select statement for census table: stmt
stmt = 'SELECT * FROM census'

# Execute the statement and fetch the results: results
results = connection.execute(stmt).fetchall()

# Print Results
print(results)

vb100

# -*- coding: utf-8 -*-
# Full instructions at: https://cambridgespark.com/content/tutorials/getting-started-with-xgboost/index.html
# Date: 20180620

#------------------------------------------------------------------------------
# Use Pandas to load the data in a dataframe
import pandas as pd
df = pd.read_excel('default of credit card clients.xls', header = 1, index_col = 0)

print('The shape of dataframe is {}.'.format(df.shape))

vb100

# -*- coding: utf-8 -*-
"""
Created on Thu Jun 21 14:26:09 2018

@author: Vytautas.Bielinskas

Definitions:
    JN - Jupyter Notebook
    ML - Machine learning
    BOG - Bag Of Words