Handle missing values in dataframe with category dtype. (#7331)

* Replace -1 in pandas initializer.
* Unify `IsValid` functor.
* Mimic pandas data handling in cuDF glue code.
* Check invalid categories.
* Fix DDM sketching.

src/data/adapter.h

@@ -21,6 +21,7 @@
 
 #include "array_interface.h"
 #include "../c_api/c_api_error.h"
+#include "../common/math.h"
 
 namespace xgboost {
 namespace data {
@@ -80,6 +81,24 @@ struct COOTuple {
   float value{0};
 };
 
+struct IsValidFunctor {
+  float missing;
+
+  XGBOOST_DEVICE explicit IsValidFunctor(float missing) : missing(missing) {}
+
+  XGBOOST_DEVICE bool operator()(float value) const {
+    return !(common::CheckNAN(value) || value == missing);
+  }
+
+  XGBOOST_DEVICE bool operator()(const data::COOTuple& e) const {
+    return !(common::CheckNAN(e.value) || e.value == missing);
+  }
+
+  XGBOOST_DEVICE bool operator()(const Entry& e) const {
+    return !(common::CheckNAN(e.fvalue) || e.fvalue == missing);
+  }
+};
+
 namespace detail {
 
 /**

src/data/data.cc

@@ -999,18 +999,19 @@ uint64_t SparsePage::Push(const AdapterBatchT& batch, float missing, int nthread
 
   // Second pass over batch, placing elements in correct position
 
+  auto is_valid = data::IsValidFunctor{missing};
 #pragma omp parallel num_threads(nthread)
   {
     exec.Run([&]() {
       int tid = omp_get_thread_num();
-      size_t begin = tid*thread_size;
-      size_t end = tid != (nthread-1) ? (tid+1)*thread_size : batch_size;
+      size_t begin = tid * thread_size;
+      size_t end = tid != (nthread - 1) ? (tid + 1) * thread_size : batch_size;
       for (size_t i = begin; i < end; ++i) {
         auto line = batch.GetLine(i);
         for (auto j = 0ull; j < line.Size(); j++) {
           auto element = line.GetElement(j);
           const size_t key = (element.row_idx - base_rowid);
-          if (!common::CheckNAN(element.value) && element.value != missing) {
+          if (is_valid(element)) {
             builder.Push(key, Entry(element.column_idx, element.value), tid);
           }
         }

src/data/device_adapter.cuh

@@ -15,29 +15,6 @@
 namespace xgboost {
 namespace data {
 
-struct IsValidFunctor : public thrust::unary_function<Entry, bool> {
-  float missing;
-
-  XGBOOST_DEVICE explicit IsValidFunctor(float missing) : missing(missing) {}
-
-  __device__ bool operator()(float value) const {
-    return !(common::CheckNAN(value) || value == missing);
-  }
-
-  __device__ bool operator()(const data::COOTuple& e) const {
-    if (common::CheckNAN(e.value) || e.value == missing) {
-      return false;
-    }
-    return true;
-  }
-  __device__ bool operator()(const Entry& e) const {
-    if (common::CheckNAN(e.fvalue) || e.fvalue == missing) {
-      return false;
-    }
-    return true;
-  }
-};
-
 class CudfAdapterBatch : public detail::NoMetaInfo {
   friend class CudfAdapter;
 

src/data/iterative_device_dmatrix.cu

@@ -152,6 +152,7 @@ void IterativeDeviceDMatrix::Initialize(DataIterHandle iter_handle, float missin
 
   if (batches == 1) {
     this->info_ = std::move(proxy->Info());
+    this->info_.num_nonzero_ = nnz;
     CHECK_EQ(proxy->Info().labels_.Size(), 0);
   }