From 6970deb103f7031841c42edb625f8750c5817ee0 Mon Sep 17 00:00:00 2001 From: Bodhi Silberling Date: Thu, 22 Jan 2026 09:34:33 -0800 Subject: [PATCH 1/4] Fix spelling errors: 'occured' -> 'occurred' and 'seperate' -> 'separate' --- .../twitter/search/earlybird/partition/SimpleStreamIndexer.java | 2 +- .../util/logging/AlertableExceptionLoggingFilter.scala | 2 +- .../tweetypie/serverutil/logcachewrites/TweetCacheWrite.scala | 2 +- tweetypie/server/src/main/thrift/tweetypie_internal.thrift | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/src/java/com/twitter/search/earlybird/partition/SimpleStreamIndexer.java b/src/java/com/twitter/search/earlybird/partition/SimpleStreamIndexer.java index 7b4e72281..6f1d16bf7 100644 --- a/src/java/com/twitter/search/earlybird/partition/SimpleStreamIndexer.java +++ b/src/java/com/twitter/search/earlybird/partition/SimpleStreamIndexer.java @@ -175,7 +175,7 @@ protected ConsumerRecords poll() { protected abstract void validateAndIndexRecord(ConsumerRecord record); - // Shutdown hook which can be called from a seperate thread. Calling consumer.wakeup() interrupts + // Shutdown hook which can be called from a separate thread. Calling consumer.wakeup() interrupts // the running indexer and causes it to first stop polling for new records before gracefully // closing the consumer. public void close() { diff --git a/tweetypie/common/src/scala/com/twitter/tweetypie/util/logging/AlertableExceptionLoggingFilter.scala b/tweetypie/common/src/scala/com/twitter/tweetypie/util/logging/AlertableExceptionLoggingFilter.scala index 0dae0bfdc..7a850aaa1 100644 --- a/tweetypie/common/src/scala/com/twitter/tweetypie/util/logging/AlertableExceptionLoggingFilter.scala +++ b/tweetypie/common/src/scala/com/twitter/tweetypie/util/logging/AlertableExceptionLoggingFilter.scala @@ -7,7 +7,7 @@ import ch.qos.logback.core.spi.FilterReply import com.twitter.tweetypie.serverutil.ExceptionCounter.isAlertable /** - * This class is currently being used by logback to log alertable exceptions to a seperate file. + * This class is currently being used by logback to log alertable exceptions to a separate file. * * Filters do not change the log levels of individual loggers. Filters filter out specific messages * for specific appenders. This allows us to have a log file with lots of information you will diff --git a/tweetypie/server/src/main/scala/com/twitter/tweetypie/serverutil/logcachewrites/TweetCacheWrite.scala b/tweetypie/server/src/main/scala/com/twitter/tweetypie/serverutil/logcachewrites/TweetCacheWrite.scala index 6f1f49cd0..61fe329f5 100644 --- a/tweetypie/server/src/main/scala/com/twitter/tweetypie/serverutil/logcachewrites/TweetCacheWrite.scala +++ b/tweetypie/server/src/main/scala/com/twitter/tweetypie/serverutil/logcachewrites/TweetCacheWrite.scala @@ -27,7 +27,7 @@ case class TweetCacheWrite( * If the tweet id is a snowflake id, this is an offset since tweet creation. * If it is not a snowflake id, then this is a Unix epoch time in * milliseconds. (The idea is that for most tweets, this encoding will make - * it easier to see the interval between events and whether it occured soon + * it easier to see the interval between events and whether it occurred soon * after tweet creation.) * - Cache action ("set", "add", "replace", "cas", "delete") * - Base64-encoded Cached[CachedTweet] struct diff --git a/tweetypie/server/src/main/thrift/tweetypie_internal.thrift b/tweetypie/server/src/main/thrift/tweetypie_internal.thrift index 3cc16381e..d5e5e5595 100644 --- a/tweetypie/server/src/main/thrift/tweetypie_internal.thrift +++ b/tweetypie/server/src/main/thrift/tweetypie_internal.thrift @@ -116,7 +116,7 @@ struct TweetCacheWrite { // If the tweet id is a snowflake id, this is an offset since tweet creation. // If it is not a snowflake id, then this is a Unix epoch time in // milliseconds. (The idea is that for most tweets, this encoding will make - // it easier to see the interval between events and whether it occured soon + // it easier to see the interval between events and whether it occurred soon // acter tweet creation.) 2: required i64 timestamp (personalDataType = 'TransactionTimestamp') 3: required string action // One of "set", "add", "replace", "cas", "delete" From e87e8446e5333a3f223f18f6fcbfe851abe65d84 Mon Sep 17 00:00:00 2001 From: Bodhi Silberling Date: Fri, 23 Jan 2026 11:04:21 -0800 Subject: [PATCH 2/4] Fix spelling errors: 'seperated' -> 'separated', 'accomodate' -> 'accommodate', 'Feture' -> 'Feature' --- navi/thrift_bpr_adapter/thrift/src/decoder.rs | 4 ++-- twml/twml/argument_parser.py | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/navi/thrift_bpr_adapter/thrift/src/decoder.rs b/navi/thrift_bpr_adapter/thrift/src/decoder.rs index 835d7d5d7..eb670cfd0 100644 --- a/navi/thrift_bpr_adapter/thrift/src/decoder.rs +++ b/navi/thrift_bpr_adapter/thrift/src/decoder.rs @@ -6,9 +6,9 @@ enum FeatureVal { FloatVector(Vec), } -// A Feture has a name and a value +// A Feature has a name and a value // The name for now is 'id' of type string -// Eventually this needs to be flexible - example to accomodate feature-id +// Eventually this needs to be flexible - example to accommodate feature-id struct Feature { id: String, val: FeatureVal, diff --git a/twml/twml/argument_parser.py b/twml/twml/argument_parser.py index c771eebdf..4db1fe89a 100644 --- a/twml/twml/argument_parser.py +++ b/twml/twml/argument_parser.py @@ -411,7 +411,7 @@ def get_trainer_parser(): action=parse_comma_separated_list(element_type=float), default=None, help="Required for 'piecewise_constant_values' learning_rate_decay. " - "A list of comma seperated floats or ints that specifies the values " + "A list of comma separated floats or ints that specifies the values " "for the intervals defined by boundaries. It should have one more " "element than boundaries.") parser_piecewise_constant.add_argument( @@ -419,7 +419,7 @@ def get_trainer_parser(): action=parse_comma_separated_list(element_type=int), default=None, help="Required for 'piecewise_constant_values' learning_rate_decay. " - "A list of comma seperated integers, with strictly increasing entries.") + "A list of comma separated integers, with strictly increasing entries.") # Create the parser for the "inverse_learning_rate_decay_fn" parser_inverse = subparsers.add_parser('inverse_learning_rate_decay', From 324e55cc795bbb81dd0bf82883dc4b6504e35036 Mon Sep 17 00:00:00 2001 From: Bodhi Silberling Date: Sun, 25 Jan 2026 10:51:11 -0800 Subject: [PATCH 3/4] Fix spelling error: 'co-occurence' -> 'co-occurrence' --- .../earlybird/queryparser/HighFrequencyTermPairExtractor.java | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/java/com/twitter/search/earlybird/queryparser/HighFrequencyTermPairExtractor.java b/src/java/com/twitter/search/earlybird/queryparser/HighFrequencyTermPairExtractor.java index 83a928185..e2df49b40 100644 --- a/src/java/com/twitter/search/earlybird/queryparser/HighFrequencyTermPairExtractor.java +++ b/src/java/com/twitter/search/earlybird/queryparser/HighFrequencyTermPairExtractor.java @@ -31,7 +31,7 @@ * opposite value of isPositive of the parent group. * * I'll try to break it down a bit further. Let's assume "a" and "b" are hf terms, and ' - * "[hf_term_pair a b]" represents querying their co-occurence. + * "[hf_term_pair a b]" represents querying their co-occurrence. * Query (* a b not_hf) can become (* [hf_term_pair a b] not_hf) * Query (+ -a -b -not_hf) can become (+ -[hf_term_pair a b] -not_hf) * These two rules represent the bulk of the rewrites that this class makes. From 820745d3523d9a618a1f177de5af15b2808845fe Mon Sep 17 00:00:00 2001 From: Bodhi Silberling Date: Sun, 25 Jan 2026 10:52:04 -0800 Subject: [PATCH 4/4] Fix typo: 'user transfer' -> 'use transfer' --- twml/twml/contrib/layers/hashed_percentile_discretizer.py | 2 +- twml/twml/contrib/layers/hashing_discretizer.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/twml/twml/contrib/layers/hashed_percentile_discretizer.py b/twml/twml/contrib/layers/hashed_percentile_discretizer.py index b32c3be8d..f42a83316 100644 --- a/twml/twml/contrib/layers/hashed_percentile_discretizer.py +++ b/twml/twml/contrib/layers/hashed_percentile_discretizer.py @@ -34,7 +34,7 @@ class HashedPercentileDiscretizer(Layer): Note that if an input feature is rarely used, so will its associated output bin/features. The difference between this layer and PercentileDiscretizer is that the DeterministicPercentileDiscretize always assigns the same output id in the SparseTensor to the - same input feature id + bin. This is useful if you want to user transfer learning on pre-trained + same input feature id + bin. This is useful if you want to use transfer learning on pre-trained sparse to dense embedding layers, but re-calibrate your discretizer on newer data. """ diff --git a/twml/twml/contrib/layers/hashing_discretizer.py b/twml/twml/contrib/layers/hashing_discretizer.py index 2a8244f4b..697901392 100644 --- a/twml/twml/contrib/layers/hashing_discretizer.py +++ b/twml/twml/contrib/layers/hashing_discretizer.py @@ -26,7 +26,7 @@ class HashingDiscretizer(Layer): The difference between this layer and PercentileDiscretizer is that the HashingDiscretizer always assigns the same output id in the SparseTensor to the same input (feature id, bin) pair. This is useful if you - want to user transfer learning on pre-trained sparse to dense embedding + want to use transfer learning on pre-trained sparse to dense embedding layers, but re-calibrate your discretizer on newer data. If there are no calibrated features, then the discretizer will only apply