[tor-commits] [metrics-tasks/master] Remove outdated censorship detector code (#2718).

[karsten at torproject.org]

commit 4426cf9cfa1d8965057c3fe34184c5ce459fa390
Author: Karsten Loesing <karsten.loesing at gmx.net>
Date:   Tue Aug 9 15:52:38 2011 +0200

    Remove outdated censorship detector code (#2718).
---
 task-2718/README                |   27 --------------------
 task-2718/convert-dirreqs-sql.R |    8 ------
 task-2718/detect-censorship.R   |   52 ---------------------------------------
 3 files changed, 0 insertions(+), 87 deletions(-)

diff --git a/task-2718/README b/task-2718/README
deleted file mode 100644
index 8c60847..0000000
--- a/task-2718/README
+++ /dev/null
@@ -1,27 +0,0 @@
-Here's how you run the censorship detector prototype:
-
-  $ wget https://metrics.torproject.org/csv/direct-users.csv
-  $ R --slave -f detect-censorship.R
-
--------------------------------------------------------------------------
-
-Extracting raw directory requests from the metrics-web database:
-
-- Export dirreq_stats table from the metrics-web database via psql:
-
-  # \f ','
-  # \a
-  # \t
-  # \o dirreqs-sql.csv
-  # SELECT * FROM dirreq_stats ORDER BY statsend;
-  # \o
-  # \t
-  # \a
-
-- Transform the huge (!) CSV file (104M) from long to wide format.  Note
-  that this takes a while:
-
-  $ R --slave -f convert-dirreqs-sql.R
-
-- The result is in dirreqs.csv (8.8M).
-
diff --git a/task-2718/convert-dirreqs-sql.R b/task-2718/convert-dirreqs-sql.R
deleted file mode 100644
index e330307..0000000
--- a/task-2718/convert-dirreqs-sql.R
+++ /dev/null
@@ -1,8 +0,0 @@
-library(ggplot2)
-data <- read.csv("dirreqs-sql.csv", header = FALSE)
-data <- data.frame(fingerprint = data$V1, statsend = data$V2,
-  seconds = data$V3, country = data$V4, requests = data$V5)
-data <- cast(data, fingerprint + statsend + seconds ~ country,
-  value = "requests")
-write.csv(data, file = "dirreqs.csv", quote = FALSE, row.names = FALSE)
-
diff --git a/task-2718/detect-censorship.R b/task-2718/detect-censorship.R
deleted file mode 100644
index f27e863..0000000
--- a/task-2718/detect-censorship.R
+++ /dev/null
@@ -1,52 +0,0 @@
-# Tor Censorship Detector
-# Usage: R --slave < detect-censorship.R
-
-# Read CSV file containing daily user number estimates.
-direct <- read.csv("direct-users.csv")
-
-# Start plotting everything to a single PDF (with multiple pages).
-pdf("detect-censorship.pdf")
-
-# Convert the column containing daily Iranian users to a time series
-# object, starting on the 263th day of 2009 with a frequency of 365 days.
-# We're probably off by a day or two, but this should be fine for now.
-all <- ts(direct$ir, start = c(2009, 263), frequency = 365)
-
-# Uncomment to print the time series values.
-#print(all)
-
-# Let's try our approach for the last 365 days to see if we detect any
-# blocking in that time period.  In the final version of this script, we'd
-# only have a single run with i = 1.
-for (i in 365:1) {
-  idx <- length(direct$date) - i
-
-  # Convert the daily Iranian users until i days in the past to a time
-  # series object.
-  x <- ts(direct$ir[1:idx], start = c(2009, 263), frequency = 365)
-
-  # Apply an ARIMA(1, 0, 1) model to the time series.
-  x.fit = arima(x, order = c(1, 0, 1))
-
-  # Predict 10 dates ahead.
-  x.fore=predict(x.fit, n.ahead=10)
-
-  # Calculate a lower bound.  Here we use the predicted value minus three
-  # standard errors.
-  L = x.fore$pred - 3*x.fore$se
-
-  # If the observed daily user number is lower than our predicted lower
-  # bound, plot the data and lower bound.
-  if (direct$ir[idx + 1] < L[1]) {
-
-    # Plot the full time series.
-    ts.plot(all)
-
-    # Add a line for the ten predicted values.
-    lines(L, col = "red", lwd = 2) 
-  }
-}
-
-# Close the PDF device.
-dev.off()
-