Merge 477e4b7756 into fb54d8b549

ann/src/main/java/com/twitter/ann/hnsw/DistancedItemQueue.java

@@ -78,7 +78,7 @@ public class DistancedItemQueue<U, T> implements Iterable<DistancedItem<T>> {
   /**
    * Return root of the queue
    *
-   * @return root of the queue i.e min/max element depending upon min-max queue
+   * @return root of the queue i.e. min/max element depending upon min-max queue
    */
   public DistancedItem<T> peek() {
     return queue.peek();
@@ -87,7 +87,7 @@ public class DistancedItemQueue<U, T> implements Iterable<DistancedItem<T>> {
   /**
    * Dequeue root of the queue.
    *
-   * @return remove and return root of the queue i.e min/max element depending upon min-max queue
+   * @return remove and return root of the queue i.e. min/max element depending upon min-max queue
    */
   public DistancedItem<T> dequeue() {
     return queue.poll();
@@ -96,7 +96,7 @@ public class DistancedItemQueue<U, T> implements Iterable<DistancedItem<T>> {
   /**
    * Dequeue all the elements from queueu with ordering mantained
    *
-   * @return remove all the elements in the order of the queue i.e min/max queue.
+   * @return remove all the elements in the order of the queue i.e. min/max queue.
    */
   public List<DistancedItem<T>> dequeueAll() {
     final List<DistancedItem<T>> list = new ArrayList<>(queue.size());

ann/src/main/scala/com/twitter/ann/scalding/offline/KnnOfflineJob.scala

@@ -14,7 +14,7 @@ import com.twitter.search.common.file.{AbstractFile, LocalFile}
 import java.util.TimeZone
 
 /**
- * Generates the nearest neighbour for users and store them in Manhattan format i.e sequence files.
+ * Generates the nearest neighbour for users and store them in Manhattan format i.e. sequence files.
  * See README for oscar usage.
  */
 object KnnOfflineJob extends TwitterExecutionApp {

ann/src/main/scala/com/twitter/ann/scalding/offline/indexbuilder/README.rst

@@ -91,7 +91,7 @@ General arguments (specified as **--profile.{options}**):
 
   3. **input.{feature_store_args}** For feature store related args like `feature_store_embedding`, `feature_store_major_version`, `date_range`:
 
-- **output_dir** Where to save the produced serialized ann index. Save to HDFS by specifying the full URI. e.g `hdfs://hadoop-dw2-nn.smf1.twitter.com/user/<user>/index_file` or using the default cluster `hdfs:///user/<user>/index_file`.
+- **output_dir** Where to save the produced serialized ann index. Save to HDFS by specifying the full URI. e.g. `hdfs://hadoop-dw2-nn.smf1.twitter.com/user/<user>/index_file` or using the default cluster `hdfs:///user/<user>/index_file`.
 - **num_dimensions** Dimension of embedding in the input data. An exception will be thrown if any entry does not have a number of dimensions equal to this number.
 - **metric** Distance metric (InnerProduct/Cosine/L2)
 - **concurrency_level** Specifies how many parallel inserts happen to the index. This should probably be set to the number of cores on the machine.

ann/src/main/scala/com/twitter/ann/service/loadtest/README.md

@@ -35,7 +35,7 @@ Load test results will be printed to stdout of an aurora job.
 # Loadtest ANN query service with query set
 
 An ANN query service can be load-tested with sample queries drawn from the embeddings dataset.
-For creating sample queries i.e `query_set` refer this [section](#query-set-generator).
+For creating sample queries i.e. `query_set` refer this [section](#query-set-generator).
 
 Test is run with `live` version of loadtest binary that is already available in packer.
 Example script to load test a ANN query service:

cr-mixer/server/src/main/scala/com/twitter/cr_mixer/model/CandidateGenerationInfo.scala

@@ -58,7 +58,7 @@ case class SimilarityEngineInfo(
  * to contribute to its final candidate list. We track these Contributing SEs in the contributingSimilarityEngines list
  *
  * @param sourceInfoOpt - this is optional as many consumerBased CG does not have a source
- * @param similarityEngineInfo - the similarity engine used in Candidate Generation (eg., TweetBasedUnifiedSE). It can be an atomic SE or an composite SE
+ * @param similarityEngineInfo - the similarity engine used in Candidate Generation (e.g., TweetBasedUnifiedSE). It can be an atomic SE or an composite SE
  * @param contributingSimilarityEngines - only composite SE will have it (e.g., SANNN, UTG). Otherwise it is an empty Seq. All contributing SEs mst be atomic
  */
 case class CandidateGenerationInfo(

cr-mixer/server/src/main/scala/com/twitter/cr_mixer/similarity_engine/ProducerBasedUnifiedSimilarityEngine.scala

@@ -352,7 +352,7 @@ object ProducerBasedUnifiedSimilarityEngine {
   /***
    * Every candidate will have the CG Info with ProducerBasedUnifiedSimilarityEngine
    * as they are generated by a composite of Similarity Engines.
-   * Additionally, we store the contributing SEs (eg., SANN, UTG).
+   * Additionally, we store the contributing SEs (e.g., SANN, UTG).
    */
   private def getProducerBasedUnifiedCGInfo(
     sourceInfoOpt: Option[SourceInfo],

cr-mixer/server/src/main/scala/com/twitter/cr_mixer/similarity_engine/TweetBasedUnifiedSimilarityEngine.scala

@@ -482,7 +482,7 @@ case class TweetBasedUnifiedSimilarityEngine(
   /***
    * Every candidate will have the CG Info with TweetBasedUnifiedSimilarityEngine
    * as they are generated by a composite of Similarity Engines.
-   * Additionally, we store the contributing SEs (eg., SANN, UTG).
+   * Additionally, we store the contributing SEs (e.g., SANN, UTG).
    */
   private def getTweetBasedUnifiedCGInfo(
     sourceInfoOpt: Option[SourceInfo],

cr-mixer/server/src/main/scala/com/twitter/cr_mixer/source_signal/SourceGraphFetcher.scala

@@ -9,7 +9,7 @@ import com.twitter.util.Future
 
 /***
  * A SourceGraphFetcher is a trait that extends from `SourceFetcher`
- * and is specialized in tackling User Graph (eg., RealGraphOon, FRS) fetch.
+ * and is specialized in tackling User Graph (e.g., RealGraphOon, FRS) fetch.
  *
  * The [[ResultType]] of a SourceGraphFetcher is a `GraphSourceInfo` which contains a userSeedSet.
  * When we pass in userId, the underlying store returns one GraphSourceInfo.

cr-mixer/server/src/main/scala/com/twitter/cr_mixer/source_signal/SourceSignalFetcher.scala

@@ -8,7 +8,7 @@ import com.twitter.util.Future
 
 /***
  * A SourceSignalFetcher is a trait that extends from `SourceFetcher`
- * and is specialized in tackling Signals (eg., USS, FRS) fetch.
+ * and is specialized in tackling Signals (e.g., USS, FRS) fetch.
  * Currently, we define Signals as (but not limited to) a set of past engagements that
  * the user makes, such as RecentFav, RecentFollow, etc.
  *

cr-mixer/server/src/main/scala/com/twitter/cr_mixer/util/MetricTagUtil.scala

@@ -121,7 +121,7 @@ object MetricTagUtil {
   /**
    * Special use case: used by Notifications team to generate the UserInterestedIn CRT push copy.
    *
-   * if we have different types of InterestedIn (eg. UserInterestedIn, NextInterestedIn),
+   * if we have different types of InterestedIn (e.g. UserInterestedIn, NextInterestedIn),
    * this if statement will have to be refactored to contain the real UserInterestedIn.
    * @return
    */

follow-recommendations-service/common/src/main/scala/com/twitter/follow_recommendations/common/models/HasUserCandidateSourceDetails.scala

@@ -7,7 +7,7 @@ import com.twitter.product_mixer.core.model.common.identifier.CandidateSourceIde
 
 /**
  * Used to keep track of a candidate's source not so much as a feature but for filtering candidate
- * from specific sources (eg. GizmoduckPredicate)
+ * from specific sources (e.g. GizmoduckPredicate)
  */
 trait HasUserCandidateSourceDetails { candidateUser: CandidateUser =>
   def userCandidateSourceDetails: Option[UserCandidateSourceDetails]

follow-recommendations-service/server/src/main/scala/com/twitter/follow_recommendations/blenders/PromotedAccountsBlender.scala

@@ -52,7 +52,7 @@ class PromotedAccountsBlender @Inject() (statsReceiver: StatsReceiver)
    * merge a list of positioned users, aka. promoted, and a list of organic
    * users.  The positioned promoted users are pre-sorted with regards to their
    * position ascendingly.  Only requirement about position is to be within the
-   * range, i.e, can not exceed the combined length if merge is successful, ok
+   * range, i.e., can not exceed the combined length if merge is successful, ok
    * to be at the last position, but not beyond.
    * For more detailed description of location position:
    * http://confluence.local.twitter.com/display/ADS/Promoted+Tweets+in+Timeline+Design+Document

follow-recommendations-service/server/src/main/scala/com/twitter/follow_recommendations/flows/post_nux_ml/PostNuxMlCombinedRankerBuilder.scala

@@ -78,7 +78,7 @@ class PostNuxMlCombinedRankerBuilder[
         randomSeed = request.getRandomizationSeed
       ).observe(weightedRankerStats)
 
-    // ranker that takes the first n results (ie truncates output) while merging duplicates
+    // ranker that takes the first n results (i.e. truncates output) while merging duplicates
     val firstNRankerObs = firstNRanker.observe(firstNRankerStats)
     // either ML ranker that uses deepbirdv2 to score or no ranking
     val mainRanker: Ranker[T, CandidateUser] =

home-mixer/server/src/main/scala/com/twitter/home_mixer/util/earlybird/EarlybirdResponseUtil.scala

@@ -324,7 +324,7 @@ object EarlybirdResponseUtil {
     }
   }
 
-  // Omitting inNetwork features e.g source tweet features and follow graph.
+  // Omitting inNetwork features e.g. source tweet features and follow graph.
   // Can be expanded to include InNetwork in the future.
   def applyOONUserDependentFeatures(
     searcherUserId: Long,

home-mixer/server/src/main/scala/com/twitter/home_mixer/util/tweetypie/content/TweetMediaFeaturesExtractor.scala

@@ -198,7 +198,7 @@ object TweetMediaFeaturesExtractor {
     }
   }.flatten
 
-  // 3rd party media providers. eg. giphy for gifs
+  // 3rd party media providers. e.g. giphy for gifs
   private def getMediaOriginProviders(mediaEntities: Seq[tp.MediaEntity]): Seq[String] =
     for {
       mediaEntity <- mediaEntities

navi/navi/proto/tensorflow/core/framework/dataset_options.proto

@@ -61,7 +61,7 @@ message CardinalityOptions {
   enum ComputeLevel {
     CARDINALITY_COMPUTE_UNSPECIFIED = 0;
     // Cardinality will only be computed if it can be determined in a cheap
-    // manner (ie. without reading from file sources). If the cardinality would
+    // manner (i.e. without reading from file sources). If the cardinality would
     // be nontrivial to compute, Cardinality() will return UNKNOWN_CARDINALITY.
     CARDINALITY_COMPUTE_LOW = 1;
     // Moderate effort will be made to determine cardinality, such as reading

navi/navi/proto/tensorflow/core/framework/variable.proto

@@ -11,7 +11,7 @@ option go_package = "github.com/tensorflow/tensorflow/tensorflow/go/core/framewo
 // Indicates when a distributed variable will be synced.
 enum VariableSynchronization {
   // `AUTO`: Indicates that the synchronization will be determined by the
-  // current `DistributionStrategy` (eg. With `MirroredStrategy` this would be
+  // current `DistributionStrategy` (e.g. With `MirroredStrategy` this would be
   // `ON_WRITE`).
   VARIABLE_SYNCHRONIZATION_AUTO = 0;
   // `NONE`: Indicates that there will only be one copy of the variable, so
@@ -21,7 +21,7 @@ enum VariableSynchronization {
   // every time it is written.
   VARIABLE_SYNCHRONIZATION_ON_WRITE = 2;
   // `ON_READ`: Indicates that the variable will be aggregated across devices
-  // when it is read (eg. when checkpointing or when evaluating an op that uses
+  // when it is read (e.g. when checkpointing or when evaluating an op that uses
   // the variable).
   VARIABLE_SYNCHRONIZATION_ON_READ = 3;
 }

navi/navi/proto/tensorflow/core/protobuf/config.proto

@@ -383,7 +383,7 @@ message RPCOptions {
 
   // Setting num_channels_per_target > 0 allows uses of multiple channels to
   // communicate to the same target. This can be used to improve the aggregate
-  // throughput on high speed links (e.g 100G) where single connection is not
+  // throughput on high speed links (e.g. 100G) where single connection is not
   // sufficient to maximize link utilization. Note that a single RPC only goes
   // on a single channel, this only helps in situations where there are multiple
   // transfers to the same target overlapping in time.

product-mixer/component-library/src/main/scala/com/twitter/product_mixer/component_library/model/candidate/CommerceItemCandidate.scala

@@ -8,7 +8,7 @@ import com.twitter.product_mixer.core.model.common.UniversalNoun
  * user clicks on a CommerceProduct, they will be taken to the specific product page.
  *
  * @note Both CommerceProduct and CommerceProductGroups (below) can be shown in the same
- *       TimelineModule (i.e Carousel)
+ *       TimelineModule (i.e. Carousel)
  *
  * @note Any additional fields should be added as a [[com.twitter.product_mixer.core.feature.Feature]]
  *       on the candidate's [[com.twitter.product_mixer.core.feature.featuremap.FeatureMap]]. If the
@@ -90,7 +90,7 @@ object CommerceProductCandidate {
  * versions of the top level product.
  *
  * @note Both CommerceProduct (above) and CommerceProductGroups can be shown in the same
- *       TimelineModule (i.e Carousel)
+ *       TimelineModule (i.e. Carousel)
  *
  * @note Any additional fields should be added as a [[com.twitter.product_mixer.core.feature.Feature]]
  *       on the candidate's [[com.twitter.product_mixer.core.feature.featuremap.FeatureMap]]. If the

product-mixer/core/src/main/scala/com/twitter/product_mixer/core/pipeline/NewPipelineArrowBuilder.scala

@@ -139,7 +139,7 @@ object NewPipelineArrowBuilder {
 }
 
 /**
- * This is a pipeline specific instance of a step, i.e, a generic step with the step identifier
+ * This is a pipeline specific instance of a step, i.e., a generic step with the step identifier
  * within the pipeline and its executor configs.
  * @param stepIdentifier Step identifier of the step within a pipeline
  * @param executorConfig Config to execute the step with

product-mixer/core/src/main/scala/com/twitter/product_mixer/core/pipeline/step/selector/SelectorStep.scala

@@ -47,7 +47,7 @@ case class SelectorStep[
     config: Seq[Selector[Query]]
   ): State = input.updateCandidatesWithDetails(executorResult.selectedCandidates)
 
-  // Selection is a bit different to other steps (i.e, other steps, empty means don't change anything)
+  // Selection is a bit different to other steps (i.e., other steps, empty means don't change anything)
   // where an empty selection list drops all candidates.
   override def isEmpty(config: Seq[Selector[Query]]): Boolean = false
 }

src/java/com/twitter/search/common/encoding/docvalues/CSFTypeUtil.java

@@ -19,7 +19,7 @@ public final class CSFTypeUtil {
    * Convert bytes into a long value. Inverse function of convertToBytes.
    */
   public static int convertFromBytes(byte[] data, int startOffset, int valueIndex) {
-    // This should rarely happen, eg. when we get a corrupt ThriftIndexingEvent, we insert a new
+    // This should rarely happen, e.g. when we get a corrupt ThriftIndexingEvent, we insert a new
     // Document which is blank. Such a document results in a length 0 BytesRef.
     if (data.length == 0) {
       return 0;

src/java/com/twitter/search/common/query/FilteredQuery.java

@@ -21,7 +21,7 @@ import org.apache.lucene.search.Weight;
  * and the filter is used only to do post-filtering. In other words, the filter is never used to
  * find the next doc ID: it's only used to filter out the doc IDs returned by the query's
  * DocIdSetIterator. This is useful when we need to have a conjunction between a query that can
- * quickly iterate through doc IDs (eg. a posting list), and an expensive filter (eg. a filter based
+ * quickly iterate through doc IDs (e.g. a posting list), and an expensive filter (e.g. a filter based
  * on the values stored in a CSF).
  *
  * For example, let say we want to build a query that returns all docs that have at least 100 faves.

src/java/com/twitter/search/common/query/QueryCommonFieldHitsVisitor.java

@@ -97,7 +97,7 @@ public final class QueryCommonFieldHitsVisitor extends SearchQueryVisitor<Set<St
         if (hits.isEmpty()) {
           // if it is empty, it means this query node is not of term type
           // and we do not include these in the field intersection
-          // eg. cache filters, proximity groups
+          // e.g. cache filters, proximity groups
           continue;
         }
         if (!initializedIntersections) {

src/java/com/twitter/search/earlybird/partition/PartitionManager.java

@@ -136,7 +136,7 @@ public abstract class PartitionManager extends OneTaskScheduledExecutorManager {
   }
 
   /**
-   * Notifies all other threads that the partition manager has become current (ie. has indexed all
+   * Notifies all other threads that the partition manager has become current (i.e. has indexed all
    * available events).
    */
   public void becomeCurrent() {

src/java/com/twitter/search/earlybird/partition/SimpleStreamIndexer.java

@@ -86,7 +86,7 @@ public abstract class SimpleStreamIndexer<K, V> {
   }
 
   /**
-   * Consume updates on startup until current (eg. until we've seen a record within 5 seconds
+   * Consume updates on startup until current (e.g. until we've seen a record within 5 seconds
    * of current time.)
    */
   public void readRecordsUntilCurrent() {

src/java/com/twitter/search/earlybird/util/TweetCountMonitor.java

@@ -49,7 +49,7 @@ import com.twitter.search.earlybird.partition.SegmentManager;
  * looks at all the createdAt dates for all of the documents in that segment.
  *
  * Also keeps track off an exposes as a stat the number of hours that do not have any tweets in the
- * min/max range of data that IS indexed on this earlybird. i.e if we only have data for
+ * min/max range of data that IS indexed on this earlybird. i.e. if we only have data for
  * 2006/01/01:02 and 2006/01/01:04, it will consider 2006/01/01:03 as a missing hour.
  * Hours before 2006/01/01:02 or after 2006/01/01:04 will not be considered as missing.
  */

src/java/com/twitter/search/earlybird_root/quota/ConfigBasedQuotaConfig.java

@@ -64,7 +64,7 @@ public class ConfigBasedQuotaConfig extends PeriodicFileLoader {
    * @param clientQuotaKey The key that will be used to extract client quotas.
    * @param requireQuotaConfigForClients Determines whether a client can be skipped
    * if the associated object is missing the quota key
-   * (ie a client that is a SuperRoot client but the current service is Archive)
+   * (i.e. a client that is a SuperRoot client but the current service is Archive)
    */
   public static ConfigBasedQuotaConfig newConfigBasedQuotaConfig(
       String quotaConfigPath,
@@ -121,7 +121,7 @@ public class ConfigBasedQuotaConfig extends PeriodicFileLoader {
       JSONObject clientQuota = quotaConfig.getJSONObject(clientId);
 
       // Skip clients that don't send requests to this service.
-      // (ie some SuperRoot clients are not Archive clients)
+      // (i.e. some SuperRoot clients are not Archive clients)
       if (!requireQuotaConfigForClients && !clientQuota.has(clientQuotaKey)) {
         continue;
       }

src/java/com/twitter/search/feature_update_service/README.md

@@ -1,5 +1,5 @@
 ## Feature Update Service
-Feature update service is a service that sends tweet feature updates e.g number of retweets, replies and favorites to Earlybird. Earlybird then indexes and uses these features to rank in-network Home Timeline tweets.
+Feature update service is a service that sends tweet feature updates e.g. number of retweets, replies and favorites to Earlybird. Earlybird then indexes and uses these features to rank in-network Home Timeline tweets.
 
 
 

src/java/com/twitter/search/ingester/pipeline/twitter/TwitterBatchedBaseStage.java

@@ -56,7 +56,7 @@ public abstract class TwitterBatchedBaseStage<T, R> extends
   protected abstract Future<Collection<R>> innerProcessBatch(Collection<BatchedElement<T, R>>
                                                                  batch);
 
-  // classes that need to update their batch e.g after a decider change
+  // classes that need to update their batch e.g. after a decider change
   // can override this
   protected void updateBatchSize() {
   }

src/scala/com/twitter/interaction_graph/scio/common/FeatureGeneratorUtil.scala

@@ -27,7 +27,7 @@ object FeatureGeneratorUtil {
 
   /**
    * Create vertex feature from InteractionGraphRawInput graph (src, dst, feature name, age, featureValue)
-   * We will represent non-directional features (eg num_create_tweets) as "outgoing" values.
+   * We will represent non-directional features (e.g., num_create_tweets) as "outgoing" values.
    * @return
    */
   def getVertexFeature(
@@ -87,7 +87,7 @@ object FeatureGeneratorUtil {
 
   /**
    * Create edge feature from InteractionGraphRawInput graph (src, dst, feature name, age, featureValue)
-   * We will exclude all non-directional features (eg num_create_tweets) from all edge aggregates
+   * We will exclude all non-directional features (e.g., num_create_tweets) from all edge aggregates
    */
   def getEdgeFeature(
     input: SCollection[InteractionGraphRawInput]

src/scala/com/twitter/interaction_graph/scio/common/UserUtil.scala

@@ -8,7 +8,7 @@ import com.twitter.usersource.snapshot.flat.thriftscala.FlatUser
 object UserUtil {
 
   /**
-   * placeholder for the destId when representing vertex features with no dest (eg create tweet)
+   * placeholder for the destId when representing vertex features with no dest (e.g., create tweet)
    * this will only be aggregated and saved in the vertex datasets but not the edge datasets
    */
   val DUMMY_USER_ID = -1L

src/scala/com/twitter/recos/user_tweet_entity_graph/README.md

@@ -5,7 +5,7 @@ User Tweet Entity Graph (UTEG) is a Finalge thrift service built on the GraphJet
 
 ## How is it used on Twitter
 UTEG generates the "XXX Liked" out-of-network tweets seen on Twitter's Home Timeline.
-The core idea behind UTEG is collaborative filtering. UTEG takes a user's weighted follow graph (i.e a list of weighted userIds) as input,
+The core idea behind UTEG is collaborative filtering. UTEG takes a user's weighted follow graph (i.e. a list of weighted userIds) as input,
 performs efficient traversal & aggregation, and returns the top-weighted tweets engaged based on # of users that engaged the tweet, as well as
 the engaged users' weights.
 

src/scala/com/twitter/recos/user_user_graph/README.md

@@ -5,7 +5,7 @@ User User Graph (UUG) is a Finalge thrift service built on the GraphJet framewor
 
 ## How is it used on Twitter
 UUG recommends users to follow based on who your follow graph have recently followed.
-The core idea behind UUG is collaborative filtering. UUG takes a user's weighted follow graph (i.e a list of weighted userIds) as input, 
+The core idea behind UUG is collaborative filtering. UUG takes a user's weighted follow graph (i.e. a list of weighted userIds) as input, 
 performs efficient traversal & aggregation, and returns the top weighted users basd on # of users that engaged the users, as well as 
 the engaging users' weights.
 

src/scala/com/twitter/simclusters_v2/scalding/embedding/abuse/DataSources.scala

@@ -95,7 +95,7 @@ object DataSources {
       case (userId, l1Norm) if l1Norm <= maxNumBlocks =>
         userId
     }
-    // retain only those users who give legit blocks (i.e those users who give less than numBlocks95)
+    // retain only those users who give legit blocks (i.e. those users who give less than numBlocks95)
     userGivingBlocks.filterRows(usersWithLegitBlocks)
   }
 }

src/scala/com/twitter/simclusters_v2/scalding/topic_recommendations/TopicsForProducersUtils.scala

@@ -14,7 +14,7 @@ object TopicsForProducersUtils {
   ] =
     Bufferable.injectionOf[(SemanticCoreEntityId, Option[Language], Option[Country])]
 
-  // This function provides the set of 'valid' topics, i.e topics with atleast a certain number of
+  // This function provides the set of 'valid' topics, i.e. topics with atleast a certain number of
   // follows. This helps remove some noisy topic associations to producers in the dataset.
   def getValidTopics(
     topicUsers: TypedPipe[((TopicId, Option[Language], Option[Country]), UserId, Double)],

src/scala/com/twitter/simclusters_v2/scalding/topic_recommendations/model_based_topic_recommendations/DataSources.scala

@@ -39,7 +39,7 @@ object DataSources {
         case KeyVal(userId, clustersUserIsInterestedIn) =>
           val clustersPostFiltering = clustersUserIsInterestedIn.clusterIdToScores.filter {
             case (clusterId, clusterScores) =>
-              // filter out popular clusters (i.e clusters with > 5M users interested in it) from the user embedding
+              // filter out popular clusters (i.e. clusters with > 5M users interested in it) from the user embedding
               clusterScores.numUsersInterestedInThisClusterUpperBound.exists(
                 _ < UserInterestedInReadableStore.MaxClusterSizeForUserInterestedInDataset)
           }

src/scala/com/twitter/simclusters_v2/scalding/update_known_for/UpdateKnownForSBFRunner.scala

@@ -567,7 +567,7 @@ object UpdateKnownForSBFRunner {
 
       val clusterAssignmentWithMaxScore: List[(ClusterId, Float)] =
         if (allClustersWithScores.length > 1) {
-          // if sparseBinaryMatrix z has rows with more than one non-zero column (i.e a user
+          // if sparseBinaryMatrix z has rows with more than one non-zero column (i.e. a user
           // initialized with more than one cluster), and the clustering algorithm doesnot find
           // a better proposal for cluster assignment, the user's multi-cluster membership
           // from the initialization step can continue.

src/thrift/com/twitter/search/earlybird/thrift/earlybird.thrift

@@ -1315,7 +1315,7 @@ struct EarlybirdDebugInfo {
   // Requests sent to dependent services. For example, superroot sends to realtime root,
   // archive root, etc.
   4: optional list<EarlybirdRequestResponse> sentRequests;
-  // segment level debug info (eg. hitsPerSegment, max/minSearchedTime etc.)
+  // segment level debug info (e.g. hitsPerSegment, max/minSearchedTime etc.)
   5: optional list<string> collectorDebugInfo
   6: optional list<string> termStatisticsDebugInfo
 }

timelineranker/common/src/main/scala/com/twitter/timelineranker/model/PartiallyHydratedTweet.scala

@@ -117,7 +117,7 @@ object PartiallyHydratedTweet {
           sourceStatusId = retweetSourceTweetId.get,
           sourceUserId = retweetSourceUserId.get,
           parentStatusId =
-            retweetSourceTweetId.get // Not always correct (eg, retweet of a retweet).
+            retweetSourceTweetId.get // Not always correct (e.g., retweet of a retweet).
         )
       )
     } else None

timelineranker/server/src/main/scala/com/twitter/timelineranker/util/TweetMediaFeatureExtractor.scala

@@ -183,7 +183,7 @@ object TweetMediaFeaturesExtractor {
     }
   }.flatten
 
-  // 3rd party media providers. eg. giphy for gifs
+  // 3rd party media providers. e.g. giphy for gifs
   private def getMediaOriginProviders(mediaEntities: Seq[MediaEntity]): Seq[String] =
     for {
       mediaEntity <- mediaEntities

twml/twml/contrib/layers/factorization_machine.py

@@ -42,7 +42,7 @@ class FactorizationMachine(Layer):
       Boolean, if `True` do sparse mat mul with `embedding_lookup_sparse`, which will
       make gradients to weight matrix also sparse in backward pass. This can lead to non-trivial
       speed up at training time when input_size is large and optimizer handles sparse gradients
-      correctly (eg. with SGD or LazyAdamOptimizer). If weight matrix is small, it's recommended
+      correctly (e.g. with SGD or LazyAdamOptimizer). If weight matrix is small, it's recommended
       to set this flag to `False`; for most use cases of FullSparse, however, weight matrix will
       be large, so it's better to set it to `True`
     use_binary_values:

twml/twml/layers/full_sparse.py

@@ -53,7 +53,7 @@ class FullSparse(Layer):
       Boolean, if `True` do sparse mat mul with `embedding_lookup_sparse`, which will
       make gradients to weight matrix also sparse in backward pass. This can lead to non-trivial
       speed up at training time when input_size is large and optimizer handles sparse gradients
-      correctly (eg. with SGD or LazyAdamOptimizer). If weight matrix is small, it's recommended
+      correctly (e.g. with SGD or LazyAdamOptimizer). If weight matrix is small, it's recommended
       to set this flag to `False`; for most use cases of FullSparse, however, weight matrix will
       be large, so it's better to set it to `True`
     num_partitions:
@@ -319,7 +319,7 @@ def full_sparse(
       Boolean, if `True` do sparse mat mul with `embedding_lookup_sparse`, which will
       make gradients to weight matrix also sparse in backward pass. This can lead to non-trivial
       speed up at training time when input_size is large and optimizer handles sparse gradients
-      correctly (eg. with SGD or LazyAdamOptimizer). If weight matrix is small, it's recommended
+      correctly (e.g. with SGD or LazyAdamOptimizer). If weight matrix is small, it's recommended
       to set this flag to `False`; for most use cases of FullSparse, however, weight matrix will
       be large, so it's better to set it to `True`
     num_partitions: