Correct spelling

.ci/test_windows.ps1

@@ -6,7 +6,7 @@ function Check-Output {
   }
 }
 
-# unify environment variable for Azure devops and AppVeyor
+# unify environment variable for Azure DevOps and AppVeyor
 if (Test-Path env:APPVEYOR) {
   $env:APPVEYOR = "true"
 }
@@ -66,7 +66,7 @@ elseif ($env:TASK -eq "sdist") {
 }
 elseif ($env:TASK -eq "bdist") {
   # Import the Chocolatey profile module so that the RefreshEnv command
-  # invoked below properly updates the current PowerShell session enviroment.
+  # invoked below properly updates the current PowerShell session environment.
   $module = "$env:ChocolateyInstall\helpers\chocolateyProfile.psm1"
   Import-Module "$module" ; Check-Output $?
   RefreshEnv

README.md

@@ -26,7 +26,7 @@ LightGBM is a gradient boosting framework that uses tree based learning algorith
 
 For further details, please refer to [Features](https://github.com/microsoft/LightGBM/blob/master/docs/Features.rst).
 
-Benefitting from these advantages, LightGBM is being widely-used in many [winning solutions](https://github.com/microsoft/LightGBM/blob/master/examples/README.md#machine-learning-challenge-winning-solutions) of machine learning competitions.
+Benefiting from these advantages, LightGBM is being widely-used in many [winning solutions](https://github.com/microsoft/LightGBM/blob/master/examples/README.md#machine-learning-challenge-winning-solutions) of machine learning competitions.
 
 [Comparison experiments](https://github.com/microsoft/LightGBM/blob/master/docs/Experiments.rst#comparison-experiment) on public datasets show that LightGBM can outperform existing boosting frameworks on both efficiency and accuracy, with significantly lower memory consumption. What's more, [distributed learning experiments](https://github.com/microsoft/LightGBM/blob/master/docs/Experiments.rst#parallel-experiment) show that LightGBM can achieve a linear speed-up by using multiple machines for training in specific settings.
 

docs/Advanced-Topics.rst

@@ -8,9 +8,9 @@ Missing Value Handle
 
 -  LightGBM uses NA (NaN) to represent missing values by default. Change it to use zero by setting ``zero_as_missing=true``.
 
--  When ``zero_as_missing=false`` (default), the unshown values in sparse matrices (and LightSVM) are treated as zeros.
+-  When ``zero_as_missing=false`` (default), the unrecorded values in sparse matrices (and LightSVM) are treated as zeros.
 
--  When ``zero_as_missing=true``, NA and zeros (including unshown values in sparse matrices (and LightSVM)) are treated as missing.
+-  When ``zero_as_missing=true``, NA and zeros (including unrecorded values in sparse matrices (and LightSVM)) are treated as missing.
 
 Categorical Feature Support
 ---------------------------

docs/Experiments.rst

@@ -194,7 +194,7 @@ We used a terabyte click log dataset to conduct parallel experiments. Details ar
 +--------+-----------------------+---------+---------------+----------+
 
 This data contains 13 integer features and 26 categorical features for 24 days of click logs.
-We statisticized the clickthrough rate (CTR) and count for these 26 categorical features from the first ten days.
+We statisticized the click-through rate (CTR) and count for these 26 categorical features from the first ten days.
 Then we used next ten days' data, after replacing the categorical features by the corresponding CTR and count, as training data.
 The processed training data have a total of 1.7 billions records and 67 features.
 

docs/Features.rst

@@ -187,7 +187,7 @@ LightGBM supports the following applications:
 
 -  cross-entropy, the objective function is logloss and supports training on non-binary labels
 
--  lambdarank, the objective function is lambdarank with NDCG
+-  LambdaRank, the objective function is LambdaRank with NDCG
 
 LightGBM supports the following metrics:
 

docs/Python-Intro.rst

@@ -1,7 +1,7 @@
 Python-package Introduction
 ===========================
 
-This document gives a basic walkthrough of LightGBM Python-package.
+This document gives a basic walk-through of LightGBM Python-package.
 
 **List of other helpful links**
 

examples/binary_classification/train.conf

@@ -7,11 +7,11 @@ boosting_type = gbdt
 # application type, support following application
 # regression , regression task
 # binary , binary classification task
-# lambdarank , lambdarank task
+# lambdarank , LambdaRank task
 # alias: application, app
 objective = binary
 
-# eval metrics, support multi metric, delimite by ',' , support following metrics
+# eval metrics, support multi metric, delimited by ',' , support following metrics
 # l1 
 # l2 , default metric for regression
 # ndcg , default metric for lambdarank
@@ -20,7 +20,7 @@ objective = binary
 # binary_error
 metric = binary_logloss,auc
 
-# frequence for metric output
+# frequency for metric output
 metric_freq = 1
 
 # true if need output metric for training data, alias: tranining_metric, train_metric
@@ -30,12 +30,12 @@ is_training_metric = true
 max_bin = 255
 
 # training data
-# if exsting weight file, should name to "binary.train.weight"
+# if existing weight file, should name to "binary.train.weight"
 # alias: train_data, train
 data = binary.train
 
 # validation data, support multi validation data, separated by ','
-# if exsting weight file, should name to "binary.test.weight"
+# if existing weight file, should name to "binary.test.weight"
 # alias: valid, test, test_data, 
 valid_data = binary.test
 
@@ -56,7 +56,7 @@ num_leaves = 63
 # alias: tree
 tree_learner = serial
 
-# number of threads for multi-threading. One thread will use one CPU, defalut is setted to #cpu. 
+# number of threads for multi-threading. One thread will use each CPU. The default is the CPU count. 
 # num_threads = 8
 
 # feature sub-sample, will random select 80% feature to train on each iteration 
@@ -66,15 +66,15 @@ feature_fraction = 0.8
 # Support bagging (data sub-sample), will perform bagging every 5 iterations
 bagging_freq = 5
 
-# Bagging farction, will random select 80% data on bagging
+# Bagging fraction, will random select 80% data on bagging
 # alias: sub_row
 bagging_fraction = 0.8
 
 # minimal number data for one leaf, use this to deal with over-fit
 # alias : min_data_per_leaf, min_data
 min_data_in_leaf = 50
 
-# minimal sum hessians for one leaf, use this to deal with over-fit
+# minimal sum Hessians for one leaf, use this to deal with over-fit
 min_sum_hessian_in_leaf = 5.0
 
 # save memory and faster speed for sparse feature, alias: is_sparse

examples/binary_classification/train_linear.conf

@@ -7,13 +7,13 @@ boosting_type = gbdt
 # application type, support following application
 # regression , regression task
 # binary , binary classification task
-# lambdarank , lambdarank task
+# lambdarank , LambdaRank task
 # alias: application, app
 objective = binary
 
 linear_tree = true
 
-# eval metrics, support multi metric, delimite by ',' , support following metrics
+# eval metrics, support multi metric, delimited by ',' , support following metrics
 # l1 
 # l2 , default metric for regression
 # ndcg , default metric for lambdarank
@@ -22,7 +22,7 @@ linear_tree = true
 # binary_error
 metric = binary_logloss,auc
 
-# frequence for metric output
+# frequency for metric output
 metric_freq = 1
 
 # true if need output metric for training data, alias: tranining_metric, train_metric
@@ -32,12 +32,12 @@ is_training_metric = true
 max_bin = 255
 
 # training data
-# if exsting weight file, should name to "binary.train.weight"
+# if existing weight file, should name to "binary.train.weight"
 # alias: train_data, train
 data = binary.train
 
 # validation data, support multi validation data, separated by ','
-# if exsting weight file, should name to "binary.test.weight"
+# if existing weight file, should name to "binary.test.weight"
 # alias: valid, test, test_data, 
 valid_data = binary.test
 
@@ -58,7 +58,7 @@ num_leaves = 63
 # alias: tree
 tree_learner = serial
 
-# number of threads for multi-threading. One thread will use one CPU, defalut is setted to #cpu. 
+# number of threads for multi-threading. One thread will use each CPU. The default is set to CPU count. 
 # num_threads = 8
 
 # feature sub-sample, will random select 80% feature to train on each iteration 
@@ -68,15 +68,15 @@ feature_fraction = 0.8
 # Support bagging (data sub-sample), will perform bagging every 5 iterations
 bagging_freq = 5
 
-# Bagging farction, will random select 80% data on bagging
+# Bagging fraction, will random select 80% data on bagging
 # alias: sub_row
 bagging_fraction = 0.8
 
 # minimal number data for one leaf, use this to deal with over-fit
 # alias : min_data_per_leaf, min_data
 min_data_in_leaf = 50
 
-# minimal sum hessians for one leaf, use this to deal with over-fit
+# minimal sum Hessians for one leaf, use this to deal with over-fit
 min_sum_hessian_in_leaf = 5.0
 
 # save memory and faster speed for sparse feature, alias: is_sparse

examples/lambdarank/README.md

@@ -1,7 +1,7 @@
 LambdaRank Example
 ==================
 
-Here is an example for LightGBM to run lambdarank task.
+Here is an example for LightGBM to run LambdaRank task.
 
 ***You must follow the [installation instructions](https://lightgbm.readthedocs.io/en/latest/Installation-Guide.html)
 for the following commands to work. The `lightgbm` binary must be built and available at the root of this project.***

examples/lambdarank/train.conf

@@ -7,11 +7,11 @@ boosting_type = gbdt
 # application type, support following application
 # regression , regression task
 # binary , binary classification task
-# lambdarank , lambdarank task
+# lambdarank , LambdaRank task
 # alias: application, app
 objective = lambdarank
 
-# eval metrics, support multi metric, delimite by ',' , support following metrics
+# eval metrics, support multi metric, delimited by ',' , support following metrics
 # l1 
 # l2 , default metric for regression
 # ndcg , default metric for lambdarank
@@ -23,7 +23,7 @@ metric = ndcg
 # evaluation position for ndcg metric, alias : ndcg_at
 ndcg_eval_at = 1,3,5
 
-# frequence for metric output
+# frequency for metric output
 metric_freq = 1
 
 # true if need output metric for training data, alias: tranining_metric, train_metric
@@ -33,14 +33,14 @@ is_training_metric = true
 max_bin = 255
 
 # training data
-# if exsting weight file, should name to "rank.train.weight"
-# if exsting query file, should name to "rank.train.query"
+# if existing weight file, should name to "rank.train.weight"
+# if existing query file, should name to "rank.train.query"
 # alias: train_data, train
 data = rank.train
 
 # validation data, support multi validation data, separated by ','
-# if exsting weight file, should name to "rank.test.weight"
-# if exsting query file, should name to "rank.test.query"
+# if existing weight file, should name to "rank.test.weight"
+# if existing query file, should name to "rank.test.query"
 # alias: valid, test, test_data, 
 valid_data = rank.test
 
@@ -71,15 +71,15 @@ feature_fraction = 1.0
 # Support bagging (data sub-sample), will perform bagging every 5 iterations
 bagging_freq = 1
 
-# Bagging farction, will random select 80% data on bagging
+# Bagging fraction, will random select 80% data on bagging
 # alias: sub_row
 bagging_fraction = 0.9
 
 # minimal number data for one leaf, use this to deal with over-fit
 # alias : min_data_per_leaf, min_data
 min_data_in_leaf = 50
 
-# minimal sum hessians for one leaf, use this to deal with over-fit
+# minimal sum Hessians for one leaf, use this to deal with over-fit
 min_sum_hessian_in_leaf = 5.0
 
 # save memory and faster speed for sparse feature, alias: is_sparse

examples/multiclass_classification/train.conf

@@ -7,12 +7,12 @@ boosting_type = gbdt
 # application type, support following application
 # regression , regression task
 # binary , binary classification task
-# lambdarank , lambdarank task
+# lambdarank , LambdaRank task
 # multiclass
 # alias: application, app
 objective = multiclass
 
-# eval metrics, support multi metric, delimite by ',' , support following metrics
+# eval metrics, support multi metric, delimited by ',' , support following metrics
 # l1 
 # l2 , default metric for regression
 # ndcg , default metric for lambdarank
@@ -35,7 +35,7 @@ auc_mu_weights = 0,1,2,3,4,5,0,6,7,8,9,10,0,11,12,13,14,15,0,16,17,18,19,20,0
 # number of class, for multiclass classification
 num_class = 5
 
-# frequence for metric output
+# frequency for metric output
 metric_freq = 1
 
 # true if need output metric for training data, alias: tranining_metric, train_metric
@@ -45,7 +45,7 @@ is_training_metric = true
 max_bin = 255
 
 # training data
-# if exsting weight file, should name to "regression.train.weight"
+# if existing weight file, should name to "regression.train.weight"
 # alias: train_data, train
 data = multiclass.train
 

examples/parallel_learning/train.conf

@@ -7,7 +7,7 @@ boosting_type = gbdt
 # application type, support following application
 # regression , regression task
 # binary , binary classification task
-# lambdarank , lambdarank task
+# lambdarank , LambdaRank task
 # alias: application, app
 objective = binary
 
@@ -20,7 +20,7 @@ objective = binary
 # binary_error
 metric = binary_logloss,auc
 
-# frequence for metric output
+# frequency for metric output
 metric_freq = 1
 
 # true if need output metric for training data, alias: tranining_metric, train_metric
@@ -30,12 +30,12 @@ is_training_metric = true
 max_bin = 255
 
 # training data
-# if exsting weight file, should name to "binary.train.weight"
+# if existing weight file, should name to "binary.train.weight"
 # alias: train_data, train
 data = binary.train
 
 # validation data, support multi validation data, separated by ','
-# if exsting weight file, should name to "binary.test.weight"
+# if existing weight file, should name to "binary.test.weight"
 # alias: valid, test, test_data, 
 valid_data = binary.test
 
@@ -56,7 +56,7 @@ num_leaves = 63
 # alias: tree
 tree_learner = feature
 
-# number of threads for multi-threading. One thread will use one CPU, defalut is setted to #cpu. 
+# number of threads for multi-threading. One thread will use each CPU. The default is the CPU count.
 # num_threads = 8
 
 # feature sub-sample, will random select 80% feature to train on each iteration 
@@ -66,15 +66,15 @@ feature_fraction = 0.8
 # Support bagging (data sub-sample), will perform bagging every 5 iterations
 bagging_freq = 5
 
-# Bagging farction, will random select 80% data on bagging
+# Bagging fraction, will random select 80% data on bagging
 # alias: sub_row
 bagging_fraction = 0.8
 
 # minimal number data for one leaf, use this to deal with over-fit
 # alias : min_data_per_leaf, min_data
 min_data_in_leaf = 50
 
-# minimal sum hessians for one leaf, use this to deal with over-fit
+# minimal sum Hessians for one leaf, use this to deal with over-fit
 min_sum_hessian_in_leaf = 5.0
 
 # save memory and faster speed for sparse feature, alias: is_sparse

examples/python-guide/advanced_example.py

@@ -93,7 +93,7 @@
 # can predict with any iteration when loaded in pickle way
 y_pred = pkl_bst.predict(X_test, num_iteration=7)
 # eval with loaded model
-print("The rmse of pickled model's prediction is:", mean_squared_error(y_test, y_pred) ** 0.5)
+print("The RMSE of pickled model's prediction is:", mean_squared_error(y_test, y_pred) ** 0.5)
 
 # continue training
 # init_model accepts:
@@ -146,7 +146,7 @@ def loglikelihood(preds, train_data):
 # f(preds: array, train_data: Dataset) -> name: string, eval_result: float, is_higher_better: bool
 # binary error
 # NOTE: when you do customized loss function, the default prediction value is margin
-# This may make built-in evalution metric calculate wrong results
+# This may make built-in evaluation metric calculate wrong results
 # For example, we are doing log likelihood loss, the prediction is score before logistic transformation
 # Keep this in mind when you use the customization
 def binary_error(preds, train_data):
@@ -170,7 +170,7 @@ def binary_error(preds, train_data):
 # f(preds: array, train_data: Dataset) -> name: string, eval_result: float, is_higher_better: bool
 # accuracy
 # NOTE: when you do customized loss function, the default prediction value is margin
-# This may make built-in evalution metric calculate wrong results
+# This may make built-in evaluation metric calculate wrong results
 # For example, we are doing log likelihood loss, the prediction is score before logistic transformation
 # Keep this in mind when you use the customization
 def accuracy(preds, train_data):