amanahuja

##
# This function calculates my bot's move in connect four algorithm
# returned mymove indicates what column to play on
# passed variable opponentmove should be the column the opponent just play on
#
# www.code-wars.com

def calculate_my_move (opponentmove): 

    if opponentmove = anything_at_all: 

amanahuja

#!/usr/bin/env python
""" 
A small class for Principal Component Analysis

@From: http://stackoverflow.com/questions/1730600/principal-component-analysis-in-python
@author Denis http://stackoverflow.com/users/86643/denis
@dated: April 2010

Usage:
    p = PCA( A, fraction=0.90 )

amanahuja

# -*- coding: utf-8 -*-
"""
Created on Thu May 22 20:30:36 2012

http://www.meetup.com/r-enthusiasts/events/65306492/
   Mirroring the work that we do in Python.
   This is the code to import the sales and query data into a Py-Pandas 
   dataframe (with conversion to time series).

Author (twitter): @amanqa

amanahuja

import feedparser
import nltk
from collections import defaultdict

#Some userful parameters
nitemstoparse = 5
new_words = []

feedurls = [
  'http://www.nytimes.com/services/xml/rss/nyt/GlobalHome.xml',

amanahuja

from sklearn.utils import check_arrays

def mean_absolute_percentage_error(y_true, y_pred): 
    """
    Use of this metric is not recommended; for illustration only. 
    See other regression metrics on sklearn docs:
      http://scikit-learn.org/stable/modules/classes.html#regression-metrics

    Use like any other metric
    >>> y_true = [3, -0.5, 2, 7]; y_pred = [2.5, -0.3, 2, 8]

amanahuja

amanahuja

import pandas as pd
import statsmodels.api as sm

#Change next two lines for dataset, such as in
#http://vincentarelbundock.github.io/Rdatasets/

data = sm.datasets.get_rdataset('airquality').data
class_column = 'Month'

fig, (ax1, ax2) = plt.subplots(nrows=2, ncols=1, sharex=True)

amanahuja

"""

Plotting a categorical variable
----------------------------------
`df` is a pandas dataframe with a timeseries index. 
`df` has a column `categorical` of dtype object, strings and nans, which is a categorical variable representing events

----------------------------------
>>> print df[:5]
                        categorical

amanahuja

amanahuja

"""
Calculation of gini coefficient metric
via https://www.kaggle.com/c/ClaimPredictionChallenge/forums/t/703/code-to-calculate-normalizedgini?forumMessageId=5897#post5897
I'm not the author, thant would be Kaggle user Patrick
See http://www.rhinorisk.com/Publications/Gini%20Coefficients.pdf 
"""
def gini(actual, pred, cmpcol = 0, sortcol = 1):
  assert( len(actual) == len(pred) )
  all = np.asarray(np.c_[ actual, pred, np.arange(len(actual)) ], dtype=np.float)
  all = all[ np.lexsort((all[:,2], -1*all[:,1])) ]