/** * @method rspamd_fann:train(inputs, outputs) * Trains neural network with samples. Inputs and outputs should be tables of * equal size, each row in table should be N inputs and M outputs, e.g. * {0, 1, 1} -> {0} * @param {table} inputs input samples * @param {table} outputs output samples * @return {number} number of samples learned */ static gint lua_fann_train (lua_State *L) { #ifndef WITH_FANN return 0; #else struct fann *f = rspamd_lua_check_fann (L, 1); guint ninputs, noutputs, j; fann_type *cur_input, *cur_output; gboolean ret = FALSE; if (f != NULL) { /* First check sanity, call for table.getn for that */ ninputs = rspamd_lua_table_size (L, 2); noutputs = rspamd_lua_table_size (L, 3); if (ninputs != fann_get_num_input (f) || noutputs != fann_get_num_output (f)) { msg_err ("bad number of inputs(%d, expected %d) and " "output(%d, expected %d) args for train", ninputs, fann_get_num_input (f), noutputs, fann_get_num_output (f)); } else { cur_input = g_malloc (ninputs * sizeof (fann_type)); for (j = 0; j < ninputs; j ++) { lua_rawgeti (L, 2, j + 1); cur_input[j] = lua_tonumber (L, -1); lua_pop (L, 1); } cur_output = g_malloc (noutputs * sizeof (fann_type)); for (j = 0; j < noutputs; j++) { lua_rawgeti (L, 3, j + 1); cur_output[j] = lua_tonumber (L, -1); lua_pop (L, 1); } fann_train (f, cur_input, cur_output); g_free (cur_input); g_free (cur_output); ret = TRUE; } } lua_pushboolean (L, ret); return 1; #endif }
/** * @method rspamd_fann:test(inputs) * Tests neural network with samples. Inputs is a single sample of input data. * The function returns table of results, e.g.: * {0, 1, 1} -> {0} * @param {table} inputs input sample * @return {table/number} outputs values */ static gint lua_fann_test (lua_State *L) { #ifndef WITH_FANN return 0; #else struct fann *f = rspamd_lua_check_fann (L, 1); guint ninputs, noutputs, i, tbl_idx = 2; fann_type *cur_input, *cur_output; if (f != NULL) { /* First check sanity, call for table.getn for that */ if (lua_isnumber (L, 2)) { ninputs = lua_tonumber (L, 2); tbl_idx = 3; } else { ninputs = rspamd_lua_table_size (L, 2); if (ninputs == 0) { msg_err ("empty inputs number"); lua_pushnil (L); return 1; } } cur_input = g_malloc0 (ninputs * sizeof (fann_type)); for (i = 0; i < ninputs; i++) { lua_rawgeti (L, tbl_idx, i + 1); cur_input[i] = lua_tonumber (L, -1); lua_pop (L, 1); } cur_output = fann_run (f, cur_input); noutputs = fann_get_num_output (f); lua_createtable (L, noutputs, 0); for (i = 0; i < noutputs; i ++) { lua_pushnumber (L, cur_output[i]); lua_rawseti (L, -2, i + 1); } g_free (cur_input); } else { lua_pushnil (L); } return 1; #endif }
static void lua_url_table_inserter (struct rspamd_url *url, gsize start_offset, gsize end_offset, gpointer ud) { lua_State *L = ud; struct rspamd_lua_url *lua_url; gint n; n = rspamd_lua_table_size (L, -1); lua_url = lua_newuserdata (L, sizeof (struct rspamd_lua_url)); rspamd_lua_setclass (L, "rspamd{url}", -1); lua_url->url = url; lua_pushinteger (L, n + 1); lua_pushlstring (L, url->string, url->urllen); lua_settable (L, -3); }
/** * @method rspamd_fann:train_threaded(inputs, outputs, callback, event_base, {params}) * Trains neural network with batch of samples. Inputs and outputs should be tables of * equal size, each row in table should be N inputs and M outputs, e.g. * {{0, 1, 1}, ...} -> {{0}, {1} ...} * @param {table} inputs input samples * @param {table} outputs output samples * @param {callback} function that is called when train is completed */ static gint lua_fann_train_threaded (lua_State *L) { #ifndef WITH_FANN return 0; #else struct fann *f = rspamd_lua_check_fann (L, 1); guint ninputs, noutputs, ndata, i, j; struct lua_fann_train_cbdata *cbdata; struct event_base *ev_base = lua_check_ev_base (L, 5); GError *err = NULL; const guint max_epochs_default = 1000; const gdouble desired_mse_default = 0.0001; if (f != NULL && lua_type (L, 2) == LUA_TTABLE && lua_type (L, 3) == LUA_TTABLE && lua_type (L, 4) == LUA_TFUNCTION && ev_base != NULL) { /* First check sanity, call for table.getn for that */ ndata = rspamd_lua_table_size (L, 2); ninputs = fann_get_num_input (f); noutputs = fann_get_num_output (f); cbdata = g_malloc0 (sizeof (*cbdata)); cbdata->L = L; cbdata->f = f; cbdata->train = rspamd_fann_create_train (ndata, ninputs, noutputs); lua_pushvalue (L, 4); cbdata->cbref = luaL_ref (L, LUA_REGISTRYINDEX); if (rspamd_socketpair (cbdata->pair, 0) == -1) { msg_err ("cannot open socketpair: %s", strerror (errno)); cbdata->pair[0] = -1; cbdata->pair[1] = -1; goto err; } for (i = 0; i < ndata; i ++) { lua_rawgeti (L, 2, i + 1); if (rspamd_lua_table_size (L, -1) != ninputs) { msg_err ("invalid number of inputs: %d, %d expected", rspamd_lua_table_size (L, -1), ninputs); goto err; } for (j = 0; j < ninputs; j ++) { lua_rawgeti (L, -1, j + 1); cbdata->train->input[i][j] = lua_tonumber (L, -1); lua_pop (L, 1); } lua_pop (L, 1); lua_rawgeti (L, 3, i + 1); if (rspamd_lua_table_size (L, -1) != noutputs) { msg_err ("invalid number of outputs: %d, %d expected", rspamd_lua_table_size (L, -1), noutputs); goto err; } for (j = 0; j < noutputs; j++) { lua_rawgeti (L, -1, j + 1); cbdata->train->output[i][j] = lua_tonumber (L, -1); lua_pop (L, 1); } } cbdata->max_epochs = max_epochs_default; cbdata->desired_mse = desired_mse_default; if (lua_type (L, 5) == LUA_TTABLE) { rspamd_lua_parse_table_arguments (L, 5, NULL, "max_epochs=I;desired_mse=N", &cbdata->max_epochs, &cbdata->desired_mse); } /* Now we can call training in a separate thread */ rspamd_socket_nonblocking (cbdata->pair[0]); event_set (&cbdata->io, cbdata->pair[0], EV_READ, lua_fann_thread_notify, cbdata); event_base_set (ev_base, &cbdata->io); /* TODO: add timeout */ event_add (&cbdata->io, NULL); cbdata->t = rspamd_create_thread ("fann train", lua_fann_train_thread, cbdata, &err); if (cbdata->t == NULL) { msg_err ("cannot create training thread: %e", err); if (err) { g_error_free (err); } goto err; } } else { return luaL_error (L, "invalid arguments"); } return 0; err: if (cbdata->pair[0] != -1) { close (cbdata->pair[0]); } if (cbdata->pair[1] != -1) { close (cbdata->pair[1]); } fann_destroy_train (cbdata->train); luaL_unref (L, LUA_REGISTRYINDEX, cbdata->cbref); g_free (cbdata); return luaL_error (L, "invalid arguments"); #endif }
/*** * @function rspamd_fann.create_full(params) * Creates new neural network with parameters: * - `layers` {table/numbers}: table of layers in form: {N1, N2, N3 ... Nn} where N is number of neurons in a layer * - `activation_hidden` {string}: activation function type for hidden layers (`tanh` by default) * - `activation_output` {string}: activation function type for output layer (`tanh` by default) * - `sparsed` {float}: create sparsed ANN, where number is a coefficient for sparsing * - `learn` {string}: learning algorithm (quickprop, rprop or incremental) * - `randomize` {boolean}: randomize weights (true by default) * @return {fann} fann object */ static gint lua_fann_create_full (lua_State *L) { #ifndef WITH_FANN return 0; #else struct fann *f, **pfann; guint nlayers, *layers, i; const gchar *activation_hidden = NULL, *activation_output, *learn_alg = NULL; gdouble sparsed = 0.0; gboolean randomize_ann = TRUE; GError *err = NULL; if (lua_type (L, 1) == LUA_TTABLE) { lua_pushstring (L, "layers"); lua_gettable (L, 1); if (lua_type (L, -1) != LUA_TTABLE) { return luaL_error (L, "bad layers attribute"); } nlayers = rspamd_lua_table_size (L, -1); if (nlayers < 2) { return luaL_error (L, "bad layers attribute"); } layers = g_new0 (guint, nlayers); for (i = 0; i < nlayers; i ++) { lua_rawgeti (L, -1, i + 1); layers[i] = luaL_checknumber (L, -1); lua_pop (L, 1); } lua_pop (L, 1); /* Table */ if (!rspamd_lua_parse_table_arguments (L, 1, &err, "sparsed=N;randomize=B;learn=S;activation_hidden=S;activation_output=S", &sparsed, &randomize_ann, &learn_alg, &activation_hidden, &activation_output)) { g_free (layers); if (err) { gint r; r = luaL_error (L, "invalid arguments: %s", err->message); g_error_free (err); return r; } else { return luaL_error (L, "invalid arguments"); } } if (sparsed != 0.0) { f = fann_create_standard_array (nlayers, layers); } else { f = fann_create_sparse_array (sparsed, nlayers, layers); } if (f != NULL) { pfann = lua_newuserdata (L, sizeof (gpointer)); *pfann = f; rspamd_lua_setclass (L, "rspamd{fann}", -1); } else { g_free (layers); return luaL_error (L, "cannot create fann"); } fann_set_activation_function_hidden (f, string_to_activation_func (activation_hidden)); fann_set_activation_function_output (f, string_to_activation_func (activation_output)); fann_set_training_algorithm (f, string_to_learn_alg (learn_alg)); if (randomize_ann) { fann_randomize_weights (f, 0, 1); } g_free (layers); } else { return luaL_error (L, "bad arguments"); } return 1; #endif }