support nan and inf in parser.

include/LightGBM/utils/common.h

@@ -80,6 +80,7 @@ inline static const char* Atoi(const char* p, int* out) {
 inline static const char* Atof(const char* p, double* out) {
   int frac;
   double sign, value, scale;
+
   // Skip leading white space, if any.
   while (*p == ' ') {
     ++p;
@@ -95,6 +96,8 @@ inline static const char* Atof(const char* p, double* out) {
     ++p;
   }
 
+  // is a number
+  if ((*p >= '0' && *p <= '9') || *p == '.' || *p == 'e' || *p == 'E') {
     // Get digits before decimal point or exponent, if any.
     for (value = 0.0; *p >= '0' && *p <= '9'; ++p) {
       value = value * 10.0 + (*p - '0');
@@ -121,8 +124,7 @@ inline static const char* Atof(const char* p, double* out) {
       if (*p == '-') {
         frac = 1;
         ++p;
-    }
-    else if (*p == '+') {
+      } else if (*p == '+') {
         ++p;
       }
       // Get digits of exponent, if any.
@@ -137,9 +139,42 @@ inline static const char* Atof(const char* p, double* out) {
     }
     // Return signed and scaled floating point result.
     *out = sign * (frac ? (value / scale) : (value * scale));
+  } else {
+    if (*p == 'n' || *p == 'N') {
+      ++p;
+      if (!(*p == 'a' || *p == 'A')) {
+        Log::Stderr("meet error while parsing string to float, expect a nan here");
+      }
+      ++p;
+      if (!(*p == 'n' || *p == 'N')) {
+        Log::Stderr("meet error while parsing string to float, expect a nan here");
+      }
+      ++p;
+      // default convert nan to 0
+      *out = 0;
+    } else if (*p == 'i' || *p == 'I') {
+      ++p;
+      if (!(*p == 'n' || *p == 'N')) {
+        Log::Stderr("meet error while parsing string to float, expect a inf here");
+      }
+      ++p;
+      if (!(*p == 'f' || *p == 'F')) {
+        Log::Stderr("meet error while parsing string to float, expect a inf here");
+      }
+      ++p;
+      // default inf
+      *out = sign * 1e308;
+    } else {
+      if (*p != '\0') {
+        Log::Stderr("Meet unknow characters while parsing string to float");
+      }
+    }
+  }
+
   while (*p == ' ') {
     ++p;
   }
+
   return p;
 }
 

src/io/parser.cpp

@@ -5,7 +5,7 @@
 
 namespace LightGBM {
 
-void GetStatistic(const char* str, int* comma_cnt, int* tab_cnt, int *colon_cnt) {
+void GetStatistic(const char* str, int* comma_cnt, int* tab_cnt, int* colon_cnt) {
   *comma_cnt = 0;
   *tab_cnt = 0;
   *colon_cnt = 0;

src/io/parser.hpp

@@ -33,13 +33,11 @@ public:
     double* out_label) const override {
     // first column is label
     str = Common::Atof(str, out_label);
-
     if (*str == ',') {
       ++str;
     } else if (*str != '\0') {
       Log::Stderr("input format error, should be CSV");
     }
-
     return ParseOneLine(str, out_features);
   }
 };
@@ -61,16 +59,14 @@ public:
     }
   }
   inline void ParseOneLine(const char* str, std::vector<std::pair<int, double>>* out_features,
-                                                           double* out_label) const override{
+    double* out_label) const override {
     // first column is label
     str = Common::Atof(str, out_label);
-
     if (*str == '\t') {
       ++str;
     } else if (*str != '\0') {
       Log::Stderr("input format error, should be TSV");
     }
-
     return ParseOneLine(str, out_features);
   }
 };
@@ -94,7 +90,7 @@ public:
     }
   }
   inline void ParseOneLine(const char* str, std::vector<std::pair<int, double>>* out_features,
-                                                            double* out_label) const override{
+    double* out_label) const override {
     // first column is label
     str = Common::Atof(str, out_label);
     str = Common::SkipSpaceAndTab(str);