Testing Code

from lxml import html, etree
import requests
import pandas as pd
import datetime as dt
import matplotlib.pyplot as plt
import RM_Super_Scraper
import re
import sqlite3
from outcodedict import urlRM, Outward

#PostCodeT = input("Postcode? : ")
# Ask for type of property advertised. asking until the answer starts with S or R
# Initialisation 
#SaleorRent = "Begin"
#while SaleorRent.upper()[0] not in ["S","R"] :
#      SaleorRent = input("Sale or Rent / S or R ? : ") 
 
PostCodeT="SW11"
SaleorRent = "S"
     
#Cut the answer to the first letter and upper case it to limit errors
SaleorRent= SaleorRent.upper()[0]
#print(SaleorRent)
#url = urlRM(Outward(PostCodeT),SaleorRent)
url='http://www.rightmove.co.uk/property-for-sale/find.html?searchType=SALE&locationIdentifier=POSTCODE%5E1602250&insId=1&radius=0.25&minPrice=&maxPrice=&minBedrooms=&maxBedrooms=&displayPropertyType=&maxDaysSinceAdded=&_includeSSTC=on&sortByPriceDescending=&primaryDisplayPropertyType=&secondaryDisplayPropertyType=&oldDisplayPropertyType=&oldPrimaryDisplayPropertyType=&newHome=&auction=false'

# Scrape the webpage
RMData = rightmove_data(url)

#print(rightmove_object.result_pages_count)
#print(rightmove_object.url)

# Create the DataFrame of results
df = RMData.get_results()

# Look at some of the results
print(set((df['date'])))


#print(rightmove_object.result_count)

# Quick look at the shape of the data.
df.describe()

# See which 'types' don't have bedroom number extracted
list(df[df.number_bedrooms.isnull()].type.unique())


# Create a DataFrame with summary statistics by number of bedrooms.
funcs = ["mean", "count"]
grouped_df = pd.DataFrame(df.groupby(["number_bedrooms"])["price"].agg(funcs).astype(int))
grouped_df.rename(columns={"mean":"average_price"}, inplace=True)
grouped_df


# Drop the outlier for plotting.
#grouped_df.drop(labels="6", axis=0, inplace=True)

# Create scatter plots to visualise price by bedroom
plt.figure(1,figsize=(10,6))
plt.scatter(df['number_bedrooms'],df['price'], c= df['house'],s=20)
plt.xlabel("Number of bedrooms")
plt.ylabel("£ Price")
# plt.ticklabel_format(style="plain")

# Create histogram chart to visualise bedroom distribution
plt.figure(num=2,figsize=(10,6))
plt.hist(df['number_bedrooms'],bins='auto',range=[0,13], normed=True,facecolor="green")
plt.xlabel("Number of bedrooms")
plt.ylabel("Density")
plt.axis([0, 14, 0, 3])
# plt.ticklabel_format(style="plain")


plt.show()