| import math | |
| import numpy | |
| import numpy.random as nrand | |
| """ | |
| Note - for some of the metrics the absolute value is returns. This is because if the risk (loss) is higher we want to | |
| discount the expected excess return from the portfolio by a higher amount. Therefore risk should be positive. | |
| """ |
First, Create a folder inside of lib called seeds
Put your CSV file example.csv into the lib/seeds folder. In the example below, the file is called real_estate_transactions.csv
Make sure you've created a resource with the appropriate columns to match your seed data. The names don't have to match up.
| ============================= | |
| **http://kickass.to/infiniteskills-learning-jquery-mobile-working-files-t7967156.html | |
| **http://kickass.to/lynda-bootstrap-3-advanced-web-development-2013-eng-t8167587.html | |
| **http://kickass.to/lynda-css-advanced-typographic-techniques-t7928210.html | |
| **http://kickass.to/lynda-html5-projects-interactive-charts-2013-eng-t8167670.html | |
| **http://kickass.to/vtc-html5-css3-responsive-web-design-course-t7922533.html | |
| *http://kickass.to/10gen-m101js-mongodb-for-node-js-developers-2013-eng-t8165205.html | |
| *http://kickass.to/cbt-nuggets-amazon-web-services-aws-foundations-t7839734.html |
| # You need to install scikit-learn: | |
| # sudo pip install scikit-learn | |
| # | |
| # Dataset: Polarity dataset v2.0 | |
| # http://www.cs.cornell.edu/people/pabo/movie-review-data/ | |
| # | |
| # Full discussion: | |
| # https://marcobonzanini.wordpress.com/2015/01/19/sentiment-analysis-with-python-and-scikit-learn |
| ''' | |
| Created on 17-Jan-2015 | |
| @author: Psycho_Coder | |
| ''' | |
| from math import sin, cos | |
| from PIL import Image | |
| import pygame, sys, os |
| # When you're sure of the format, it's much quicker to explicitly convert your dates than use `parse_dates` | |
| # Makes sense; was just surprised by the time difference. | |
| import pandas as pd | |
| from datetime import datetime | |
| to_datetime = lambda d: datetime.strptime(d, '%m/%d/%Y %H:%M') | |
| %time trips = pd.read_csv('data/divvy/Divvy_Trips_2013.csv', parse_dates=['starttime', 'stoptime']) | |
| # CPU times: user 1min 29s, sys: 331 ms, total: 1min 29s | |
| # Wall time: 1min 30s |
| import pandas | |
| import logging | |
| def multi_df_join(df_dict): | |
| """ | |
| Takes a list of dataframes with the same primary key (id) and merges the columns, using | |
| the dictionary keys as suffixes in case there are conflicts with the column names. | |
| :param df_dict: A dictionary where keys are strings (collision suffixes) and values are DataFrames | |
| :return pandas.DataFrame: The merged data frames |
| """ | |
| Multiclass SVMs (Crammer-Singer formulation). | |
| A pure Python re-implementation of: | |
| Large-scale Multiclass Support Vector Machine Training via Euclidean Projection onto the Simplex. | |
| Mathieu Blondel, Akinori Fujino, and Naonori Ueda. | |
| ICPR 2014. | |
| http://www.mblondel.org/publications/mblondel-icpr2014.pdf | |
| """ |
A personal diary of DataFrame munging over the years.
Convert Series datatype to numeric (will error if column has non-numeric values)
(h/t @makmanalp)
| #!/usr/bin/env python | |
| import sys | |
| import pandas as pd | |
| import pymongo | |
| import json | |
| def import_content(filepath): | |
| mng_client = pymongo.MongoClient('localhost', 27017) |
