Merge pull request #64 from Allardvm/master

Improved consistency and wording of user-facing logs and documentation

src/network/network.cpp

@@ -30,7 +30,7 @@ void Network::Init(NetworkConfig config) {
   block_len_ = new int[num_machines_];
   buffer_size_ = 1024 * 1024;
   buffer_ = new char[buffer_size_];
-  Log::Info("local rank %d, total number of machines %d", rank_, num_machines_);
+  Log::Info("Local rank: %d, total number of machines: %d", rank_, num_machines_);
 }
 
 void Network::Dispose() {

src/network/socket_wrapper.hpp

@@ -60,7 +60,7 @@ public:
   TcpSocket() {
     sockfd_ = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
     if (sockfd_ == INVALID_SOCKET) {
-      Log::Fatal("Socket construct error");
+      Log::Fatal("Socket construction error");
       return;
     }
     ConfigSocket();
@@ -97,7 +97,7 @@ public:
 #if defined(_WIN32)
     WSADATA wsa_data;
     if (WSAStartup(MAKEWORD(2, 2), &wsa_data) == -1) {
-      Log::Fatal("Socket error: WSAStart up error");
+      Log::Fatal("Socket error: WSAStartup error");
     }
     if (LOBYTE(wsa_data.wVersion) != 2 || HIBYTE(wsa_data.wVersion) != 2) {
       WSACleanup();
@@ -128,7 +128,7 @@ public:
     char buffer[512];
     // get hostName
     if (gethostname(buffer, sizeof(buffer)) == SOCKET_ERROR) {
-      Log::Fatal("Error code: %d, when getting local host name.", WSAGetLastError());
+      Log::Fatal("Error code %d, when getting local host name", WSAGetLastError());
     }
     // push local ip
     PIP_ADAPTER_INFO pAdapterInfo;
@@ -137,7 +137,7 @@ public:
     ULONG ulOutBufLen = sizeof(IP_ADAPTER_INFO);
     pAdapterInfo = (IP_ADAPTER_INFO *)MALLOC(sizeof(IP_ADAPTER_INFO));
     if (pAdapterInfo == NULL) {
-      Log::Fatal("GetAdaptersinfo error: allocating memory ");
+      Log::Fatal("GetAdaptersinfo error: allocating memory");
     }
     // Make an initial call to GetAdaptersInfo to get
     // the necessary size into the ulOutBufLen variable
@@ -145,7 +145,7 @@ public:
       FREE(pAdapterInfo);
       pAdapterInfo = (IP_ADAPTER_INFO *)MALLOC(ulOutBufLen);
       if (pAdapterInfo == NULL) {
-        Log::Fatal("GetAdaptersinfo error: allocating memory ");
+        Log::Fatal("GetAdaptersinfo error: allocating memory");
       }
     }
     if ((dwRetVal = GetAdaptersInfo(pAdapterInfo, &ulOutBufLen)) == NO_ERROR) {
@@ -155,7 +155,7 @@ public:
         pAdapter = pAdapter->Next;
       }
     } else {
-      Log::Fatal("GetAdaptersinfo error: code %d ", dwRetVal);
+      Log::Fatal("GetAdaptersinfo error: code %d", dwRetVal);
     }
     if (pAdapterInfo)
       FREE(pAdapterInfo);

src/objective/binary_objective.hpp

@@ -16,7 +16,7 @@ public:
     is_unbalance_ = config.is_unbalance;
     sigmoid_ = static_cast<score_t>(config.sigmoid);
     if (sigmoid_ <= 0.0) {
-      Log::Fatal("Sigmoid parameter %f :should greater than zero", sigmoid_);
+      Log::Fatal("Sigmoid parameter %f should be greater than zero", sigmoid_);
     }
   }
   ~BinaryLogloss() {}
@@ -34,10 +34,10 @@ public:
         ++cnt_negative;
       }
     }
-    Log::Info("Number of postive:%d,  number of negative:%d", cnt_positive, cnt_negative);
+    Log::Info("Number of postive: %d, number of negative: %d", cnt_positive, cnt_negative);
     // cannot continue if all sample are same class
     if (cnt_positive == 0 || cnt_negative == 0) {
-      Log::Fatal("Input training data only contains one class");
+      Log::Fatal("Training data only contains one class");
     }
     // use -1 for negative class, and 1 for positive class
     label_val_[0] = -1;

src/objective/multiclass_objective.hpp

@@ -16,20 +16,20 @@ public:
         :label_int_(nullptr) {
     num_class_ = config.num_class;
   }
-  
+
   ~MulticlassLogloss() {
-    if (label_int_ != nullptr) { delete[] label_int_; }    
+    if (label_int_ != nullptr) { delete[] label_int_; }
   }
-  
+
   void Init(const Metadata& metadata, data_size_t num_data) override {
     num_data_ = num_data;
     label_ = metadata.label();
     weights_ = metadata.weights();
     label_int_ = new int[num_data_];
     for (int i = 0; i < num_data_; ++i){
-        label_int_[i] = static_cast<int>(label_[i]); 
+        label_int_[i] = static_cast<int>(label_[i]);
         if (label_int_[i] < 0 || label_int_[i] >= num_class_) {
-            Log::Fatal("Label must be in [0, %d), but find %d in label", num_class_, label_int_[i]);
+            Log::Fatal("Label must be in [0, %d), but found %d in label", num_class_, label_int_[i]);
         }
     }
   }
@@ -42,7 +42,7 @@ public:
         for (int k = 0; k < num_class_; ++k){
           rec[k] = static_cast<double>(score[k * num_data_ + i]);
         }
-        Common::Softmax(&rec);  
+        Common::Softmax(&rec);
         for (int k = 0; k < num_class_; ++k) {
           score_t p = static_cast<score_t>(rec[k]);
           if (label_int_[i] == k) {
@@ -51,7 +51,7 @@ public:
             gradients[k * num_data_ + i] = p;
           }
           hessians[k * num_data_ + i] = 2.0f * p * (1.0f - p);
-        }  
+        }
       }
     } else {
       #pragma omp parallel for schedule(static)
@@ -59,7 +59,7 @@ public:
         std::vector<double> rec(num_class_);
         for (int k = 0; k < num_class_; ++k){
           rec[k] = static_cast<double>(score[k * num_data_ + i]);
-        }  
+        }
         Common::Softmax(&rec);
         for (int k = 0; k < num_class_; ++k) {
           score_t p = static_cast<score_t>(rec[k]);

src/objective/rank_objective.hpp

@@ -31,7 +31,7 @@ public:
     optimize_pos_at_ = config.max_position;
     sigmoid_table_ = nullptr;
     if (sigmoid_ <= 0.0) {
-      Log::Fatal("sigmoid param %f should greater than zero", sigmoid_);
+      Log::Fatal("Sigmoid param %f should be greater than zero", sigmoid_);
     }
   }
   ~LambdarankNDCG() {
@@ -47,7 +47,7 @@ public:
     // get boundries
     query_boundaries_ = metadata.query_boundaries();
     if (query_boundaries_ == nullptr) {
-      Log::Fatal("For lambdarank tasks, should have query information");
+      Log::Fatal("Lambdarank tasks require query information");
     }
     num_queries_ = metadata.num_queries();
     // cache inverse max DCG, avoid computation many times

src/treelearner/serial_tree_learner.cpp

@@ -112,7 +112,7 @@ void SerialTreeLearner::Init(const Dataset* train_data) {
   if (has_ordered_bin_) {
     is_data_in_leaf_ = new char[num_data_];
   }
-  Log::Info("Number of data:%d, Number of features:%d", num_data_, num_features_);
+  Log::Info("Number of data: %d, number of features: %d", num_data_, num_features_);
 }
 
 
@@ -142,7 +142,7 @@ Tree* SerialTreeLearner::Train(const score_t* gradients, const score_t *hessians
     const SplitInfo& best_leaf_SplitInfo = best_split_per_leaf_[best_leaf];
     // cannot split, quit
     if (best_leaf_SplitInfo.gain <= 0.0) {
-      Log::Info("cannot find more split with gain = %f , current #leaves=%d",
+      Log::Info("No further splits with positive gain, best gain: %f, leaves: %d",
                    best_leaf_SplitInfo.gain, split + 1);
       break;
     }
@@ -266,7 +266,7 @@ bool SerialTreeLearner::BeforeFindBestSplit(int left_leaf, int right_leaf) {
   if (right_leaf < 0) {
     histogram_pool_.Get(left_leaf, &smaller_leaf_histogram_array_);
     larger_leaf_histogram_array_ = nullptr;
-    
+
   } else if (num_data_in_left_child < num_data_in_right_child) {
     smaller_leaf = left_leaf;
     larger_leaf = right_leaf;

src/treelearner/split_info.hpp

@@ -40,13 +40,13 @@ public:
   double right_sum_hessian;
 
   SplitInfo() {
-    // initilize with -1 and -inf gain
+    // initialize with -1 and -inf gain
     feature = -1;
     gain = kMinScore;
   }
 
   inline void Reset() {
-    // initilize with -1 and -inf gain
+    // initialize with -1 and -inf gain
     feature = -1;
     gain = kMinScore;
   }