pygments.rb 0.6.3 → 1.0.0

data/vendor/pygments-main/tests/examplefiles/test.pig

@@ -1,148 +0,0 @@
-/**
- *  This script is an example recommender (using made up data) showing how you might modify item-item links
- *  by defining similar relations between items in a dataset and customizing the change in weighting.
- *  This example creates metadata by using the genre field as the metadata_field.  The items with
- *  the same genre have it's weight cut in half in order to boost the signals of movies that do not have the same genre.
- *  This technique requires a customization of the standard GetItemItemRecommendations macro
- */
-import 'recommenders.pig';
-
-
-
-%default INPUT_PATH_PURCHASES '../data/retail/purchases.json'
-%default INPUT_PATH_WISHLIST '../data/retail/wishlists.json'
-%default INPUT_PATH_INVENTORY '../data/retail/inventory.json'
-%default OUTPUT_PATH '../data/retail/out/modify_item_item'
-
-
-/******** Custom GetItemItemRecommnedations *********/
-define recsys__GetItemItemRecommendations_ModifyCustom(user_item_signals, metadata) returns item_item_recs {
-
-    -- Convert user_item_signals to an item_item_graph
-    ii_links_raw, item_weights   =   recsys__BuildItemItemGraph(
-                                       $user_item_signals,
-                                       $LOGISTIC_PARAM,
-                                       $MIN_LINK_WEIGHT,
-                                       $MAX_LINKS_PER_USER
-                                     );
-    -- NOTE this function is added in order to combine metadata with item-item links
-        -- See macro for more detailed explination
-    ii_links_metadata           =   recsys__AddMetadataToItemItemLinks(
-                                        ii_links_raw,
-                                        $metadata
-                                    );
-
-    /********* Custom Code starts here ********/
-
-    --The code here should adjust the weights based on an item-item link and the equality of metadata.
-    -- In this case, if the metadata is the same, the weight is reduced.  Otherwise the weight is left alone.
-    ii_links_adjusted           =  foreach ii_links_metadata generate item_A, item_B,
-                                        -- the amount of weight adjusted is dependant on the domain of data and what is expected
-                                        -- It is always best to adjust the weight by multiplying it by a factor rather than addition with a constant
-                                        (metadata_B == metadata_A ? (weight * 0.5): weight) as weight;
-
-
-    /******** Custom Code stops here *********/
-
-    -- remove negative numbers just incase
-    ii_links_adjusted_filt = foreach ii_links_adjusted generate item_A, item_B,
-                                      (weight <= 0 ? 0: weight) as weight;
-    -- Adjust the weights of the graph to improve recommendations.
-    ii_links                    =   recsys__AdjustItemItemGraphWeight(
-                                        ii_links_adjusted_filt,
-                                        item_weights,
-                                        $BAYESIAN_PRIOR
-                                    );
-
-    -- Use the item-item graph to create item-item recommendations.
-    $item_item_recs =  recsys__BuildItemItemRecommendationsFromGraph(
-                           ii_links,
-                           $NUM_RECS_PER_ITEM,
-                           $NUM_RECS_PER_ITEM
-                       );
-};
-
-
-/******* Load Data **********/
-
---Get purchase signals
-purchase_input = load '$INPUT_PATH_PURCHASES' using org.apache.pig.piggybank.storage.JsonLoader(
-                    'row_id: int,
-                     movie_id: chararray,
-                     movie_name: chararray,
-                     user_id: chararray,
-                     purchase_price: int');
-
---Get wishlist signals
-wishlist_input =  load '$INPUT_PATH_WISHLIST' using org.apache.pig.piggybank.storage.JsonLoader(
-                     'row_id: int,
-                      movie_id: chararray,
-                      movie_name: chararray,
-                      user_id: chararray');
-
-
-/******* Convert Data to Signals **********/
-
--- Start with choosing 1 as max weight for a signal.
-purchase_signals = foreach purchase_input generate
-                        user_id    as user,
-                        movie_name as item,
-                        1.0        as weight;
-
-
--- Start with choosing 0.5 as weight for wishlist items because that is a weaker signal than
--- purchasing an item.
-wishlist_signals = foreach wishlist_input generate
-                        user_id    as user,
-                        movie_name as item,
-                        0.5        as weight;
-
-user_signals = union purchase_signals, wishlist_signals;
-
-
-/******** Changes for Modifying item-item links ******/
-inventory_input = load '$INPUT_PATH_INVENTORY' using org.apache.pig.piggybank.storage.JsonLoader(
-                     'movie_title: chararray,
-                      genres: bag{tuple(content:chararray)}');
-
-
-metadata = foreach inventory_input generate
-              FLATTEN(genres) as metadata_field,
-              movie_title as item;
--- requires the macro to be written seperately
-  --NOTE this macro is defined within this file for clarity
-item_item_recs = recsys__GetItemItemRecommendations_ModifyCustom(user_signals, metadata);
-/******* No more changes ********/
-
-
-user_item_recs = recsys__GetUserItemRecommendations(user_signals, item_item_recs);
-
---Completely unrelated code stuck in the middle
-data        =    LOAD 's3n://my-s3-bucket/path/to/responses'
-                 USING org.apache.pig.piggybank.storage.JsonLoader();
-responses   =    FOREACH data GENERATE object#'response' AS response: map[];
-out         =    FOREACH responses
-                 GENERATE response#'id' AS id: int, response#'thread' AS thread: chararray,
-                          response#'comments' AS comments: {t: (comment: chararray)};
-STORE out INTO 's3n://path/to/output' USING PigStorage('|');
-
-
-/******* Store recommendations **********/
-
---  If your output folder exists already, hadoop will refuse to write data to it.
-
-rmf $OUTPUT_PATH/item_item_recs;
-rmf $OUTPUT_PATH/user_item_recs;
-
-store item_item_recs into '$OUTPUT_PATH/item_item_recs' using PigStorage();
-store user_item_recs into '$OUTPUT_PATH/user_item_recs' using PigStorage();
-
--- STORE the item_item_recs into dynamo
-STORE item_item_recs
- INTO '$OUTPUT_PATH/unused-ii-table-data'
-USING com.mortardata.pig.storage.DynamoDBStorage('$II_TABLE', '$AWS_ACCESS_KEY_ID', '$AWS_SECRET_ACCESS_KEY');
-
--- STORE the user_item_recs into dynamo
-STORE user_item_recs
- INTO '$OUTPUT_PATH/unused-ui-table-data'
-USING com.mortardata.pig.storage.DynamoDBStorage('$UI_TABLE', '$AWS_ACCESS_KEY_ID', '$AWS_SECRET_ACCESS_KEY');

data/vendor/pygments-main/tests/examplefiles/test.plot

@@ -1,333 +0,0 @@
-#
-# $Id: prob2.dem,v 1.9 2006/06/14 03:24:09 sfeam Exp $
-#
-# Demo Statistical Approximations version 1.1
-#
-# Copyright (c) 1991, Jos van der Woude, jvdwoude@hut.nl
-
-# History:
-#    -- --- 1991 Jos van der Woude:  1st version
-#    06 Jun 2006 Dan Sebald:  Added plot methods for better visual effect.
-
-print ""
-print ""
-print ""
-print ""
-print ""
-print ""
-print "                        Statistical Approximations, version 1.1"
-print ""
-print "        Copyright (c) 1991, 1992, Jos van de Woude, jvdwoude@hut.nl"
-print ""
-print ""
-print ""
-print ""
-print ""
-print ""
-print ""
-print ""
-print ""
-print ""
-print ""
-print "     NOTE: contains 10 plots and consequently takes some time to run"
-print "                      Press Ctrl-C to exit right now"
-print ""
-pause -1 "                      Press Return to start demo ..."
-
-load "stat.inc"
-rnd(x) = floor(x+0.5)
-r_xmin = -1
-r_sigma = 4.0
-
-# Binomial PDF using normal approximation
-n = 25; p = 0.15
-mu = n * p
-sigma = sqrt(n * p * (1.0 - p))
-xmin = floor(mu - r_sigma * sigma)
-xmin = xmin < r_xmin ? r_xmin : xmin
-xmax = ceil(mu + r_sigma * sigma)
-ymax = 1.1 * binom(floor((n+1)*p), n, p) #mode of binomial PDF used
-set key box
-unset zeroaxis
-set xrange [xmin - 1 : xmax + 1]
-set yrange [0 : ymax]
-set xlabel "k, x ->"
-set ylabel "probability density ->"
-set ytics 0, ymax / 10.0, ymax
-set format x "%2.0f"
-set format y "%3.2f"
-set sample 200
-set title "binomial PDF using normal approximation"
-set arrow from mu, 0 to mu, normal(mu, mu, sigma) nohead
-set arrow from mu, normal(mu + sigma, mu, sigma) \
-          to mu + sigma, normal(mu + sigma, mu, sigma) nohead
-set label "mu" at mu + 0.5, ymax / 10
-set label "sigma" at mu + 0.5 + sigma, normal(mu + sigma, mu, sigma)
-plot binom(rnd(x), n, p) with histeps, normal(x, mu, sigma)
-pause -1 "Hit return to continue"
-unset arrow
-unset label
-
-# Binomial PDF using poisson approximation
-n = 50; p = 0.1
-mu = n * p
-sigma = sqrt(mu)
-xmin = floor(mu - r_sigma * sigma)
-xmin = xmin < r_xmin ? r_xmin : xmin
-xmax = ceil(mu + r_sigma * sigma)
-ymax = 1.1 * binom(floor((n+1)*p), n, p) #mode of binomial PDF used
-set key box
-unset zeroaxis
-set xrange [xmin - 1 : xmax + 1]
-set yrange [0 : ymax]
-set xlabel "k ->"
-set ylabel "probability density ->"
-set ytics 0, ymax / 10.0, ymax
-set format x "%2.0f"
-set format y "%3.2f"
-set sample (xmax - xmin + 3)
-set title "binomial PDF using poisson approximation"
-set arrow from mu, 0 to mu, normal(mu, mu, sigma) nohead
-set arrow from mu, normal(mu + sigma, mu, sigma) \
-          to mu + sigma, normal(mu + sigma, mu, sigma) nohead
-set label "mu" at mu + 0.5, ymax / 10
-set label "sigma" at mu + 0.5 + sigma, normal(mu + sigma, mu, sigma)
-plot binom(x, n, p) with histeps, poisson(x, mu) with histeps
-pause -1 "Hit return to continue"
-unset arrow
-unset label
-
-# Geometric PDF using gamma approximation
-p = 0.3
-mu = (1.0 - p) / p
-sigma = sqrt(mu / p)
-lambda = p
-rho = 1.0 - p
-xmin = floor(mu - r_sigma * sigma)
-xmin = xmin < r_xmin ? r_xmin : xmin
-xmax = ceil(mu + r_sigma * sigma)
-ymax = 1.1 * p
-set key box
-unset zeroaxis
-set xrange [xmin - 1 : xmax + 1]
-set yrange [0 : ymax]
-set xlabel "k, x ->"
-set ylabel "probability density ->"
-set ytics 0, ymax / 10.0, ymax
-set format x "%2.0f"
-set format y "%3.2f"
-set sample 200
-set title "geometric PDF using gamma approximation"
-set arrow from mu, 0 to mu, gmm(mu, rho, lambda) nohead
-set arrow from mu, gmm(mu + sigma, rho, lambda) \
-          to mu + sigma, gmm(mu + sigma, rho, lambda) nohead
-set label "mu" at mu + 0.5, ymax / 10
-set label "sigma" at mu + 0.5 + sigma, gmm(mu + sigma, rho, lambda)
-plot geometric(rnd(x),p) with histeps, gmm(x, rho, lambda)
-pause -1 "Hit return to continue"
-unset arrow
-unset label
-
-# Geometric PDF using normal approximation
-p = 0.3
-mu = (1.0 - p) / p
-sigma = sqrt(mu / p)
-xmin = floor(mu - r_sigma * sigma)
-xmin = xmin < r_xmin ? r_xmin : xmin
-xmax = ceil(mu + r_sigma * sigma)
-ymax = 1.1 * p
-set key box
-unset zeroaxis
-set xrange [xmin - 1 : xmax + 1]
-set yrange [0 : ymax]
-set xlabel "k, x ->"
-set ylabel "probability density ->"
-set ytics 0, ymax / 10.0, ymax
-set format x "%2.0f"
-set format y "%3.2f"
-set sample 200
-set title "geometric PDF using normal approximation"
-set arrow from mu, 0 to mu, normal(mu, mu, sigma) nohead
-set arrow from mu, normal(mu + sigma, mu, sigma) \
-          to mu + sigma, normal(mu + sigma, mu, sigma) nohead
-set label "mu" at mu + 0.5, ymax / 10
-set label "sigma" at mu + 0.5 + sigma, normal(mu + sigma, mu, sigma)
-plot geometric(rnd(x),p) with histeps, normal(x, mu, sigma)
-pause -1 "Hit return to continue"
-unset arrow
-unset label
-
-# Hypergeometric PDF using binomial approximation
-nn = 75; mm = 25; n = 10
-p = real(mm) / nn
-mu = n * p
-sigma = sqrt(real(nn - n) / (nn - 1.0) * n * p * (1.0 - p))
-xmin = floor(mu - r_sigma * sigma)
-xmin = xmin < r_xmin ? r_xmin : xmin
-xmax = ceil(mu + r_sigma * sigma)
-ymax = 1.1 * hypgeo(floor(mu), nn, mm, n) #mode of binom PDF used
-set key box
-unset zeroaxis
-set xrange [xmin - 1 : xmax + 1]
-set yrange [0 : ymax]
-set xlabel "k ->"
-set ylabel "probability density ->"
-set ytics 0, ymax / 10.0, ymax
-set format x "%2.0f"
-set format y "%3.2f"
-set sample (xmax - xmin + 3)
-set title "hypergeometric PDF using binomial approximation"
-set arrow from mu, 0 to mu, binom(floor(mu), n, p) nohead
-set arrow from mu, binom(floor(mu + sigma), n, p) \
-          to mu + sigma, binom(floor(mu + sigma), n, p) nohead
-set label "mu" at mu + 0.5, ymax / 10
-set label "sigma" at mu + 0.5 + sigma, binom(floor(mu + sigma), n, p)
-plot hypgeo(x, nn, mm, n) with histeps, binom(x, n, p) with histeps
-pause -1 "Hit return to continue"
-unset arrow
-unset label
-
-# Hypergeometric PDF using normal approximation
-nn = 75; mm = 25; n = 10
-p = real(mm) / nn
-mu = n * p
-sigma = sqrt(real(nn - n) / (nn - 1.0) * n * p * (1.0 - p))
-xmin = floor(mu - r_sigma * sigma)
-xmin = xmin < r_xmin ? r_xmin : xmin
-xmax = ceil(mu + r_sigma * sigma)
-ymax = 1.1 * hypgeo(floor(mu), nn, mm, n) #mode of binom PDF used
-set key box
-unset zeroaxis
-set xrange [xmin - 1 : xmax + 1]
-set yrange [0 : ymax]
-set xlabel "k, x ->"
-set ylabel "probability density ->"
-set ytics 0, ymax / 10.0, ymax
-set format x "%2.0f"
-set format y "%3.2f"
-set sample 200
-set title "hypergeometric PDF using normal approximation"
-set arrow from mu, 0 to mu, normal(mu, mu, sigma) nohead
-set arrow from mu, normal(mu + sigma, mu, sigma) \
-          to mu + sigma, normal(mu + sigma, mu, sigma) nohead
-set label "mu" at mu + 0.5, ymax / 10
-set label "sigma" at mu + 0.5 + sigma, normal(mu + sigma, mu, sigma)
-plot hypgeo(rnd(x), nn, mm, n) with histeps, normal(x, mu, sigma)
-pause -1 "Hit return to continue"
-unset arrow
-unset label
-
-# Negative binomial PDF using gamma approximation
-r = 8; p = 0.6
-mu = r * (1.0 - p) / p
-sigma = sqrt(mu / p)
-lambda = p
-rho = r * (1.0 - p)
-xmin = floor(mu - r_sigma * sigma)
-xmin = xmin < r_xmin ? r_xmin : xmin
-xmax = ceil(mu + r_sigma * sigma)
-ymax = 1.1 * gmm((rho - 1) / lambda, rho, lambda) #mode of gamma PDF used
-set key box
-unset zeroaxis
-set xrange [xmin - 1 : xmax + 1]
-set yrange [0 : ymax]
-set xlabel "k, x ->"
-set ylabel "probability density ->"
-set ytics 0, ymax / 10.0, ymax
-set format x "%2.0f"
-set format y "%3.2f"
-set sample 200
-set title "negative binomial PDF using gamma approximation"
-set arrow from mu, 0 to mu, gmm(mu, rho, lambda) nohead
-set arrow from mu, gmm(mu + sigma, rho, lambda) \
-          to mu + sigma, gmm(mu + sigma, rho, lambda) nohead
-set label "mu" at mu + 0.5, ymax / 10
-set label "sigma" at mu + 0.5 + sigma, gmm(mu + sigma, rho, lambda)
-plot negbin(rnd(x), r, p) with histeps, gmm(x, rho, lambda)
-pause -1 "Hit return to continue"
-unset arrow
-unset label
-
-# Negative binomial PDF using normal approximation
-r = 8; p = 0.4
-mu = r * (1.0 - p) / p
-sigma = sqrt(mu / p)
-xmin = floor(mu - r_sigma * sigma)
-xmin = xmin < r_xmin ? r_xmin : xmin
-xmax = ceil(mu + r_sigma * sigma)
-ymax = 1.1 * negbin(floor((r-1)*(1-p)/p), r, p) #mode of gamma PDF used
-set key box
-unset zeroaxis
-set xrange [xmin - 1 : xmax + 1]
-set yrange [0 : ymax]
-set xlabel "k, x ->"
-set ylabel "probability density ->"
-set ytics 0, ymax / 10.0, ymax
-set format x "%2.0f"
-set format y "%3.2f"
-set sample 200
-set title "negative binomial PDF using normal approximation"
-set arrow from mu, 0 to mu, normal(mu, mu, sigma) nohead
-set arrow from mu, normal(mu + sigma, mu, sigma) \
-          to mu + sigma, normal(mu + sigma, mu, sigma) nohead
-set label "mu" at mu + 0.5, ymax / 10
-set label "sigma" at mu + 0.5 + sigma, normal(mu + sigma, mu, sigma)
-plot negbin(rnd(x), r, p) with histeps, normal(x, mu, sigma)
-pause -1 "Hit return to continue"
-unset arrow
-unset label
-
-# Normal PDF using logistic approximation
-mu = 1.0; sigma = 1.5
-a = mu
-lambda = pi / (sqrt(3.0) * sigma)
-xmin = mu - r_sigma * sigma
-xmax = mu + r_sigma * sigma
-ymax = 1.1 * logistic(mu, a, lambda) #mode of logistic PDF used
-set key box
-unset zeroaxis
-set xrange [xmin: xmax]
-set yrange [0 : ymax]
-set xlabel "x ->"
-set ylabel "probability density ->"
-set ytics 0, ymax / 10.0, ymax
-set format x "%.1f"
-set format y "%.2f"
-set sample 200
-set title "normal PDF using logistic approximation"
-set arrow from mu,0 to mu, normal(mu, mu, sigma) nohead
-set arrow from mu, normal(mu + sigma, mu, sigma) \
-          to mu + sigma, normal(mu + sigma, mu, sigma) nohead
-set label "mu" at mu + 0.5, ymax / 10
-set label "sigma" at mu + 0.5 + sigma, normal(mu + sigma, mu, sigma)
-plot logistic(x, a, lambda), normal(x, mu, sigma)
-pause -1 "Hit return to continue"
-unset arrow
-unset label
-
-# Poisson PDF using normal approximation
-mu = 5.0
-sigma = sqrt(mu)
-xmin = floor(mu - r_sigma * sigma)
-xmin = xmin < r_xmin ? r_xmin : xmin
-xmax = ceil(mu + r_sigma * sigma)
-ymax = 1.1 * poisson(mu, mu) #mode of poisson PDF used
-set key box
-unset zeroaxis
-set xrange [xmin - 1 : xmax + 1]
-set yrange [0 : ymax]
-set xlabel "k, x ->"
-set ylabel "probability density ->"
-set ytics 0, ymax / 10.0, ymax
-set format x "%2.0f"
-set format y "%3.2f"
-set sample 200
-set title "poisson PDF using normal approximation"
-set arrow from mu, 0 to mu, normal(mu, mu, sigma) nohead
-set arrow from mu, normal(mu + sigma, mu, sigma) \
-          to mu + sigma, normal(mu + sigma, mu, sigma) nohead
-set label "mu" at mu + 0.5, ymax / 10
-set label "sigma" at mu + 0.5 + sigma, normal(mu + sigma, mu, sigma)
-plot poisson(rnd(x), mu) with histeps, normal(x, mu, sigma)
-pause -1 "Hit return to continue"
-reset