{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Self made simplified I-KNN" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import helpers\n", "import pandas as pd\n", "import numpy as np\n", "import scipy.sparse as sparse\n", "from collections import defaultdict\n", "from itertools import chain\n", "import random\n", "\n", "train_read = pd.read_csv(\"./Datasets/ml-100k/train.csv\", sep=\"\\t\", header=None)\n", "test_read = pd.read_csv(\"./Datasets/ml-100k/test.csv\", sep=\"\\t\", header=None)\n", "(\n", " train_ui,\n", " test_ui,\n", " user_code_id,\n", " user_id_code,\n", " item_code_id,\n", " item_id_code,\n", ") = helpers.data_to_csr(train_read, test_read)" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "class IKNN:\n", " def fit(self, train_ui):\n", " self.train_ui = train_ui\n", "\n", " train_iu = train_ui.transpose()\n", " norms = np.linalg.norm(\n", " train_iu.A, axis=1\n", " ) # here we compute length of each item ratings vector\n", " norms = np.vectorize(lambda x: max(x, 1))(\n", " norms[:, None]\n", " ) # to avoid dividing by zero\n", "\n", " normalized_train_iu = sparse.csr_matrix(train_iu / norms)\n", "\n", " self.similarity_matrix_ii = (\n", " normalized_train_iu * normalized_train_iu.transpose()\n", " )\n", "\n", " self.estimations = np.array(\n", " train_ui\n", " * self.similarity_matrix_ii\n", " / ((train_ui > 0) * self.similarity_matrix_ii)\n", " )\n", "\n", " def recommend(self, user_code_id, item_code_id, topK=10):\n", "\n", " top_k = defaultdict(list)\n", " for nb_user, user in enumerate(self.estimations):\n", "\n", " user_rated = self.train_ui.indices[\n", " self.train_ui.indptr[nb_user] : self.train_ui.indptr[nb_user + 1]\n", " ]\n", " for item, score in enumerate(user):\n", " if item not in user_rated and not np.isnan(score):\n", " top_k[user_code_id[nb_user]].append((item_code_id[item], score))\n", " result = []\n", " # Let's choose k best items in the format: (user, item1, score1, item2, score2, ...)\n", " for uid, item_scores in top_k.items():\n", " item_scores.sort(key=lambda x: x[1], reverse=True)\n", " result.append([uid] + list(chain(*item_scores[:topK])))\n", " return result\n", "\n", " def estimate(self, user_code_id, item_code_id, test_ui):\n", " result = []\n", " for user, item in zip(*test_ui.nonzero()):\n", " result.append(\n", " [\n", " user_code_id[user],\n", " item_code_id[item],\n", " self.estimations[user, item]\n", " if not np.isnan(self.estimations[user, item])\n", " else 1,\n", " ]\n", " )\n", " return result" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "toy train ui:\n" ] }, { "data": { "text/plain": [ "array([[3, 4, 0, 0, 5, 0, 0, 4],\n", " [0, 1, 2, 3, 0, 0, 0, 0],\n", " [0, 0, 0, 5, 0, 3, 4, 0]])" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "similarity matrix:\n" ] }, { "data": { "text/plain": [ "array([[1. , 0.9701425 , 0. , 0. , 1. ,\n", " 0. , 0. , 1. ],\n", " [0.9701425 , 1. , 0.24253563, 0.12478355, 0.9701425 ,\n", " 0. , 0. , 0.9701425 ],\n", " [0. , 0.24253563, 1. , 0.51449576, 0. ,\n", " 0. , 0. , 0. ],\n", " [0. , 0.12478355, 0.51449576, 1. , 0. ,\n", " 0.85749293, 0.85749293, 0. ],\n", " [1. , 0.9701425 , 0. , 0. , 1. ,\n", " 0. , 0. , 1. ],\n", " [0. , 0. , 0. , 0.85749293, 0. ,\n", " 1. , 1. , 0. ],\n", " [0. , 0. , 0. , 0.85749293, 0. ,\n", " 1. , 1. , 0. ],\n", " [1. , 0.9701425 , 0. , 0. , 1. ,\n", " 0. , 0. , 1. ]])" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "estimations matrix:\n" ] }, { "data": { "text/plain": [ "array([[4. , 4. , 4. , 4. , 4. ,\n", " nan, nan, 4. ],\n", " [1. , 1.35990333, 2.15478388, 2.53390319, 1. ,\n", " 3. , 3. , 1. ],\n", " [ nan, 5. , 5. , 4.05248907, nan,\n", " 3.95012863, 3.95012863, nan]])" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [ "[[0, 20, 4.0, 30, 4.0],\n", " [10, 50, 3.0, 60, 3.0, 0, 1.0, 40, 1.0, 70, 1.0],\n", " [20, 10, 5.0, 20, 5.0]]" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# toy example\n", "toy_train_read = pd.read_csv(\n", " \"./Datasets/toy-example/train.csv\",\n", " sep=\"\\t\",\n", " header=None,\n", " names=[\"user\", \"item\", \"rating\", \"timestamp\"],\n", ")\n", "toy_test_read = pd.read_csv(\n", " \"./Datasets/toy-example/test.csv\",\n", " sep=\"\\t\",\n", " header=None,\n", " names=[\"user\", \"item\", \"rating\", \"timestamp\"],\n", ")\n", "\n", "(\n", " toy_train_ui,\n", " toy_test_ui,\n", " toy_user_code_id,\n", " toy_user_id_code,\n", " toy_item_code_id,\n", " toy_item_id_code,\n", ") = helpers.data_to_csr(toy_train_read, toy_test_read)\n", "\n", "\n", "model = IKNN()\n", "model.fit(toy_train_ui)\n", "\n", "print(\"toy train ui:\")\n", "display(toy_train_ui.A)\n", "\n", "print(\"similarity matrix:\")\n", "display(model.similarity_matrix_ii.A)\n", "\n", "print(\"estimations matrix:\")\n", "display(model.estimations)\n", "\n", "model.recommend(toy_user_code_id, toy_item_code_id)" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "model = IKNN()\n", "model.fit(train_ui)\n", "\n", "top_n = pd.DataFrame(model.recommend(user_code_id, item_code_id, topK=10))\n", "\n", "top_n.to_csv(\n", " \"Recommendations generated/ml-100k/Self_IKNN_reco.csv\", index=False, header=False\n", ")\n", "\n", "estimations = pd.DataFrame(model.estimate(user_code_id, item_code_id, test_ui))\n", "estimations.to_csv(\n", " \"Recommendations generated/ml-100k/Self_IKNN_estimations.csv\",\n", " index=False,\n", " header=False,\n", ")" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "943it [00:00, 8588.04it/s]\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
RMSEMAEprecisionrecallF_1F_05precision_superrecall_superNDCGmAPMRRLAUCHRH2RReco in testTest coverageShannonGini
01.0183630.8087930.0003180.0001080.000140.0001890.00.00.0002140.0000370.0003680.4963910.0031810.00.3921530.115444.1747410.965327
\n", "
" ], "text/plain": [ " RMSE MAE precision recall F_1 F_05 \\\n", "0 1.018363 0.808793 0.000318 0.000108 0.00014 0.000189 \n", "\n", " precision_super recall_super NDCG mAP MRR LAUC \\\n", "0 0.0 0.0 0.000214 0.000037 0.000368 0.496391 \n", "\n", " HR H2R Reco in test Test coverage Shannon Gini \n", "0 0.003181 0.0 0.392153 0.11544 4.174741 0.965327 " ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import evaluation_measures as ev\n", "\n", "estimations_df = pd.read_csv(\n", " \"Recommendations generated/ml-100k/Self_IKNN_estimations.csv\", header=None\n", ")\n", "reco = np.loadtxt(\"Recommendations generated/ml-100k/Self_IKNN_reco.csv\", delimiter=\",\")\n", "\n", "ev.evaluate(\n", " test=pd.read_csv(\"./Datasets/ml-100k/test.csv\", sep=\"\\t\", header=None),\n", " estimations_df=estimations_df,\n", " reco=reco,\n", " super_reactions=[4, 5],\n", ")" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "943it [00:00, 7583.88it/s]\n", "943it [00:00, 7223.78it/s]\n", "943it [00:00, 8277.93it/s]\n", "943it [00:00, 7896.23it/s]\n", "943it [00:00, 8398.64it/s]\n", "943it [00:00, 8514.79it/s]\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
ModelRMSEMAEprecisionrecallF_1F_05precision_superrecall_superNDCGmAPMRRLAUCHRH2RReco in testTest coverageShannonGini
0Self_TopPop2.5082582.2179090.1888650.1169190.1187320.1415840.1304720.1374730.2146510.1117070.4009390.5555460.7656420.4920471.0000000.0389613.1590790.987317
0Ready_Baseline0.9494590.7524870.0914100.0376520.0460300.0612860.0796140.0564630.0959570.0431780.1981930.5155010.4379640.2396611.0000000.0339112.8365130.991139
0Ready_Random1.5215571.2226530.0467660.0213570.0241130.0314410.0274680.0212470.0507150.0196350.1211850.5071910.3149520.1092260.9885470.1883125.0945690.908346
0Self_TopRated1.0307120.8209040.0009540.0001880.0002980.0004810.0006440.0002230.0010430.0003350.0033480.4964330.0095440.0000000.6990460.0050511.9459100.995669
0Self_BaselineUI0.9675850.7627400.0009540.0001700.0002780.0004630.0006440.0001890.0007520.0001680.0016770.4964240.0095440.0000000.6005300.0050511.8031260.996380
0Self_IKNN1.0183630.8087930.0003180.0001080.0001400.0001890.0000000.0000000.0002140.0000370.0003680.4963910.0031810.0000000.3921530.1154404.1747410.965327
\n", "
" ], "text/plain": [ " Model RMSE MAE precision recall F_1 \\\n", "0 Self_TopPop 2.508258 2.217909 0.188865 0.116919 0.118732 \n", "0 Ready_Baseline 0.949459 0.752487 0.091410 0.037652 0.046030 \n", "0 Ready_Random 1.521557 1.222653 0.046766 0.021357 0.024113 \n", "0 Self_TopRated 1.030712 0.820904 0.000954 0.000188 0.000298 \n", "0 Self_BaselineUI 0.967585 0.762740 0.000954 0.000170 0.000278 \n", "0 Self_IKNN 1.018363 0.808793 0.000318 0.000108 0.000140 \n", "\n", " F_05 precision_super recall_super NDCG mAP MRR \\\n", "0 0.141584 0.130472 0.137473 0.214651 0.111707 0.400939 \n", "0 0.061286 0.079614 0.056463 0.095957 0.043178 0.198193 \n", "0 0.031441 0.027468 0.021247 0.050715 0.019635 0.121185 \n", "0 0.000481 0.000644 0.000223 0.001043 0.000335 0.003348 \n", "0 0.000463 0.000644 0.000189 0.000752 0.000168 0.001677 \n", "0 0.000189 0.000000 0.000000 0.000214 0.000037 0.000368 \n", "\n", " LAUC HR H2R Reco in test Test coverage Shannon \\\n", "0 0.555546 0.765642 0.492047 1.000000 0.038961 3.159079 \n", "0 0.515501 0.437964 0.239661 1.000000 0.033911 2.836513 \n", "0 0.507191 0.314952 0.109226 0.988547 0.188312 5.094569 \n", "0 0.496433 0.009544 0.000000 0.699046 0.005051 1.945910 \n", "0 0.496424 0.009544 0.000000 0.600530 0.005051 1.803126 \n", "0 0.496391 0.003181 0.000000 0.392153 0.115440 4.174741 \n", "\n", " Gini \n", "0 0.987317 \n", "0 0.991139 \n", "0 0.908346 \n", "0 0.995669 \n", "0 0.996380 \n", "0 0.965327 " ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dir_path = \"Recommendations generated/ml-100k/\"\n", "super_reactions = [4, 5]\n", "test = pd.read_csv(\"./Datasets/ml-100k/test.csv\", sep=\"\\t\", header=None)\n", "\n", "ev.evaluate_all(test, dir_path, super_reactions)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Ready-made KNNs - Surprise implementation" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### I-KNN - basic" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Computing the cosine similarity matrix...\n", "Done computing similarity matrix.\n", "Generating predictions...\n", "Generating top N recommendations...\n", "Generating predictions...\n" ] } ], "source": [ "import helpers\n", "import surprise as sp\n", "\n", "sim_options = {\n", " \"name\": \"cosine\",\n", " \"user_based\": False,\n", "} # compute similarities between items\n", "algo = sp.KNNBasic(sim_options=sim_options)\n", "\n", "helpers.ready_made(\n", " algo,\n", " reco_path=\"Recommendations generated/ml-100k/Ready_I-KNN_reco.csv\",\n", " estimations_path=\"Recommendations generated/ml-100k/Ready_I-KNN_estimations.csv\",\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### U-KNN - basic" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Computing the cosine similarity matrix...\n", "Done computing similarity matrix.\n", "Generating predictions...\n", "Generating top N recommendations...\n", "Generating predictions...\n" ] } ], "source": [ "sim_options = {\n", " \"name\": \"cosine\",\n", " \"user_based\": True,\n", "} # compute similarities between users\n", "algo = sp.KNNBasic(sim_options=sim_options)\n", "\n", "helpers.ready_made(\n", " algo,\n", " reco_path=\"Recommendations generated/ml-100k/Ready_U-KNN_reco.csv\",\n", " estimations_path=\"Recommendations generated/ml-100k/Ready_U-KNN_estimations.csv\",\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### I-KNN - on top baseline" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Estimating biases using als...\n", "Computing the msd similarity matrix...\n", "Done computing similarity matrix.\n", "Generating predictions...\n", "Generating top N recommendations...\n", "Generating predictions...\n" ] } ], "source": [ "sim_options = {\n", " \"name\": \"cosine\",\n", " \"user_based\": False,\n", "} # compute similarities between items\n", "algo = sp.KNNBaseline()\n", "\n", "helpers.ready_made(\n", " algo,\n", " reco_path=\"Recommendations generated/ml-100k/Ready_I-KNNBaseline_reco.csv\",\n", " estimations_path=\"Recommendations generated/ml-100k/Ready_I-KNNBaseline_estimations.csv\",\n", ")" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "943it [00:00, 7365.70it/s]\n", "943it [00:00, 7711.28it/s]\n", "943it [00:00, 8040.96it/s]\n", "943it [00:00, 7229.39it/s]\n", "943it [00:00, 7471.94it/s]\n", "943it [00:00, 7835.57it/s]\n", "943it [00:00, 7384.15it/s]\n", "943it [00:00, 7682.96it/s]\n", "943it [00:00, 8110.98it/s]\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
ModelRMSEMAEprecisionrecallF_1F_05precision_superrecall_superNDCGmAPMRRLAUCHRH2RReco in testTest coverageShannonGini
0Self_TopPop2.5082582.2179090.1888650.1169190.1187320.1415840.1304720.1374730.2146510.1117070.4009390.5555460.7656420.4920471.0000000.0389613.1590790.987317
0Ready_Baseline0.9494590.7524870.0914100.0376520.0460300.0612860.0796140.0564630.0959570.0431780.1981930.5155010.4379640.2396611.0000000.0339112.8365130.991139
0Ready_Random1.5215571.2226530.0467660.0213570.0241130.0314410.0274680.0212470.0507150.0196350.1211850.5071910.3149520.1092260.9885470.1883125.0945690.908346
0Ready_I-KNN1.0303860.8130670.0260870.0069080.0105930.0160460.0211370.0095220.0242140.0089580.0480680.4998850.1548250.0721100.4023330.4343435.1336500.877999
0Ready_I-KNNBaseline0.9353270.7374240.0025450.0007550.0011050.0016020.0022530.0009300.0034440.0013620.0117600.4967240.0212090.0042420.4828210.0598852.2325780.994487
0Ready_U-KNN1.0234950.8079130.0007420.0002050.0003050.0004490.0005360.0001980.0008450.0002740.0027440.4964410.0074230.0000000.6021210.0108232.0891860.995706
0Self_TopRated1.0307120.8209040.0009540.0001880.0002980.0004810.0006440.0002230.0010430.0003350.0033480.4964330.0095440.0000000.6990460.0050511.9459100.995669
0Self_BaselineUI0.9675850.7627400.0009540.0001700.0002780.0004630.0006440.0001890.0007520.0001680.0016770.4964240.0095440.0000000.6005300.0050511.8031260.996380
0Self_IKNN1.0183630.8087930.0003180.0001080.0001400.0001890.0000000.0000000.0002140.0000370.0003680.4963910.0031810.0000000.3921530.1154404.1747410.965327
\n", "
" ], "text/plain": [ " Model RMSE MAE precision recall F_1 \\\n", "0 Self_TopPop 2.508258 2.217909 0.188865 0.116919 0.118732 \n", "0 Ready_Baseline 0.949459 0.752487 0.091410 0.037652 0.046030 \n", "0 Ready_Random 1.521557 1.222653 0.046766 0.021357 0.024113 \n", "0 Ready_I-KNN 1.030386 0.813067 0.026087 0.006908 0.010593 \n", "0 Ready_I-KNNBaseline 0.935327 0.737424 0.002545 0.000755 0.001105 \n", "0 Ready_U-KNN 1.023495 0.807913 0.000742 0.000205 0.000305 \n", "0 Self_TopRated 1.030712 0.820904 0.000954 0.000188 0.000298 \n", "0 Self_BaselineUI 0.967585 0.762740 0.000954 0.000170 0.000278 \n", "0 Self_IKNN 1.018363 0.808793 0.000318 0.000108 0.000140 \n", "\n", " F_05 precision_super recall_super NDCG mAP MRR \\\n", "0 0.141584 0.130472 0.137473 0.214651 0.111707 0.400939 \n", "0 0.061286 0.079614 0.056463 0.095957 0.043178 0.198193 \n", "0 0.031441 0.027468 0.021247 0.050715 0.019635 0.121185 \n", "0 0.016046 0.021137 0.009522 0.024214 0.008958 0.048068 \n", "0 0.001602 0.002253 0.000930 0.003444 0.001362 0.011760 \n", "0 0.000449 0.000536 0.000198 0.000845 0.000274 0.002744 \n", "0 0.000481 0.000644 0.000223 0.001043 0.000335 0.003348 \n", "0 0.000463 0.000644 0.000189 0.000752 0.000168 0.001677 \n", "0 0.000189 0.000000 0.000000 0.000214 0.000037 0.000368 \n", "\n", " LAUC HR H2R Reco in test Test coverage Shannon \\\n", "0 0.555546 0.765642 0.492047 1.000000 0.038961 3.159079 \n", "0 0.515501 0.437964 0.239661 1.000000 0.033911 2.836513 \n", "0 0.507191 0.314952 0.109226 0.988547 0.188312 5.094569 \n", "0 0.499885 0.154825 0.072110 0.402333 0.434343 5.133650 \n", "0 0.496724 0.021209 0.004242 0.482821 0.059885 2.232578 \n", "0 0.496441 0.007423 0.000000 0.602121 0.010823 2.089186 \n", "0 0.496433 0.009544 0.000000 0.699046 0.005051 1.945910 \n", "0 0.496424 0.009544 0.000000 0.600530 0.005051 1.803126 \n", "0 0.496391 0.003181 0.000000 0.392153 0.115440 4.174741 \n", "\n", " Gini \n", "0 0.987317 \n", "0 0.991139 \n", "0 0.908346 \n", "0 0.877999 \n", "0 0.994487 \n", "0 0.995706 \n", "0 0.995669 \n", "0 0.996380 \n", "0 0.965327 " ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dir_path = \"Recommendations generated/ml-100k/\"\n", "super_reactions = [4, 5]\n", "test = pd.read_csv(\"./Datasets/ml-100k/test.csv\", sep=\"\\t\", header=None)\n", "\n", "ev.evaluate_all(test, dir_path, super_reactions)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# project task 3: use a version of your choice of Surprise KNNalgorithm" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [], "source": [ "# read the docs and try to find best parameter configuration (let say in terms of RMSE)\n", "# https://surprise.readthedocs.io/en/stable/knn_inspired.html##surprise.prediction_algorithms.knns.KNNBaseline\n", "# the solution here can be similar to examples above\n", "# please save the output in 'Recommendations generated/ml-100k/Self_KNNSurprisetask_reco.csv' and\n", "# 'Recommendations generated/ml-100k/Self_KNNSurprisetask_estimations.csv'" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Computing the msd similarity matrix...\n", "Done computing similarity matrix.\n", "Generating predictions...\n", "Generating top N recommendations...\n", "Generating predictions...\n" ] } ], "source": [ "import helpers\n", "import surprise as sp\n", "import imp\n", "import evaluation_measures as ev\n", "\n", "sim_options = {\n", " \"name\": \"cosine\",\n", " \"user_based\": False,\n", "} \n", "algo = sp.KNNWithZScore(k=60) #decent, but not the highest :(\n", "\n", "helpers.ready_made(\n", " algo, \n", " reco_path='Recommendations generated/ml-100k/Ready_I-KNNWithZScore_reco.csv',\n", " estimations_path='Recommendations generated/ml-100k/Ready_I-KNNWithZScore_estimations.csv')" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "943it [00:00, 7524.72it/s]\n", "943it [00:00, 7502.87it/s]\n", "943it [00:00, 8263.30it/s]\n", "943it [00:00, 6706.49it/s]\n", "943it [00:00, 7512.76it/s]\n", "943it [00:00, 8251.80it/s]\n", "943it [00:00, 8527.56it/s]\n", "943it [00:00, 8427.52it/s]\n", "943it [00:00, 8499.27it/s]\n", "943it [00:00, 8530.84it/s]\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
ModelRMSEMAEprecisionrecallF_1F_05precision_superrecall_superNDCGmAPMRRLAUCHRH2RReco in testTest coverageShannonGini
0Self_TopPop2.5082582.2179090.1888650.1169190.1187320.1415840.1304720.1374730.2146510.1117070.4009390.5555460.7656420.4920471.0000000.0389613.1590790.987317
0Ready_Baseline0.9494590.7524870.0914100.0376520.0460300.0612860.0796140.0564630.0959570.0431780.1981930.5155010.4379640.2396611.0000000.0339112.8365130.991139
0Ready_Random1.5215571.2226530.0467660.0213570.0241130.0314410.0274680.0212470.0507150.0196350.1211850.5071910.3149520.1092260.9885470.1883125.0945690.908346
0Ready_I-KNN1.0303860.8130670.0260870.0069080.0105930.0160460.0211370.0095220.0242140.0089580.0480680.4998850.1548250.0721100.4023330.4343435.1336500.877999
0Ready_I-KNNWithZScore0.9567360.7512150.0039240.0021340.0025130.0030780.0037550.0026330.0049060.0020650.0136210.4974190.0265110.0084840.3872750.0613282.4272880.993420
0Ready_I-KNNBaseline0.9353270.7374240.0025450.0007550.0011050.0016020.0022530.0009300.0034440.0013620.0117600.4967240.0212090.0042420.4828210.0598852.2325780.994487
0Ready_U-KNN1.0234950.8079130.0007420.0002050.0003050.0004490.0005360.0001980.0008450.0002740.0027440.4964410.0074230.0000000.6021210.0108232.0891860.995706
0Self_TopRated1.0307120.8209040.0009540.0001880.0002980.0004810.0006440.0002230.0010430.0003350.0033480.4964330.0095440.0000000.6990460.0050511.9459100.995669
0Self_BaselineUI0.9675850.7627400.0009540.0001700.0002780.0004630.0006440.0001890.0007520.0001680.0016770.4964240.0095440.0000000.6005300.0050511.8031260.996380
0Self_IKNN1.0183630.8087930.0003180.0001080.0001400.0001890.0000000.0000000.0002140.0000370.0003680.4963910.0031810.0000000.3921530.1154404.1747410.965327
\n", "
" ], "text/plain": [ " Model RMSE MAE precision recall F_1 \\\n", "0 Self_TopPop 2.508258 2.217909 0.188865 0.116919 0.118732 \n", "0 Ready_Baseline 0.949459 0.752487 0.091410 0.037652 0.046030 \n", "0 Ready_Random 1.521557 1.222653 0.046766 0.021357 0.024113 \n", "0 Ready_I-KNN 1.030386 0.813067 0.026087 0.006908 0.010593 \n", "0 Ready_I-KNNWithZScore 0.956736 0.751215 0.003924 0.002134 0.002513 \n", "0 Ready_I-KNNBaseline 0.935327 0.737424 0.002545 0.000755 0.001105 \n", "0 Ready_U-KNN 1.023495 0.807913 0.000742 0.000205 0.000305 \n", "0 Self_TopRated 1.030712 0.820904 0.000954 0.000188 0.000298 \n", "0 Self_BaselineUI 0.967585 0.762740 0.000954 0.000170 0.000278 \n", "0 Self_IKNN 1.018363 0.808793 0.000318 0.000108 0.000140 \n", "\n", " F_05 precision_super recall_super NDCG mAP MRR \\\n", "0 0.141584 0.130472 0.137473 0.214651 0.111707 0.400939 \n", "0 0.061286 0.079614 0.056463 0.095957 0.043178 0.198193 \n", "0 0.031441 0.027468 0.021247 0.050715 0.019635 0.121185 \n", "0 0.016046 0.021137 0.009522 0.024214 0.008958 0.048068 \n", "0 0.003078 0.003755 0.002633 0.004906 0.002065 0.013621 \n", "0 0.001602 0.002253 0.000930 0.003444 0.001362 0.011760 \n", "0 0.000449 0.000536 0.000198 0.000845 0.000274 0.002744 \n", "0 0.000481 0.000644 0.000223 0.001043 0.000335 0.003348 \n", "0 0.000463 0.000644 0.000189 0.000752 0.000168 0.001677 \n", "0 0.000189 0.000000 0.000000 0.000214 0.000037 0.000368 \n", "\n", " LAUC HR H2R Reco in test Test coverage Shannon \\\n", "0 0.555546 0.765642 0.492047 1.000000 0.038961 3.159079 \n", "0 0.515501 0.437964 0.239661 1.000000 0.033911 2.836513 \n", "0 0.507191 0.314952 0.109226 0.988547 0.188312 5.094569 \n", "0 0.499885 0.154825 0.072110 0.402333 0.434343 5.133650 \n", "0 0.497419 0.026511 0.008484 0.387275 0.061328 2.427288 \n", "0 0.496724 0.021209 0.004242 0.482821 0.059885 2.232578 \n", "0 0.496441 0.007423 0.000000 0.602121 0.010823 2.089186 \n", "0 0.496433 0.009544 0.000000 0.699046 0.005051 1.945910 \n", "0 0.496424 0.009544 0.000000 0.600530 0.005051 1.803126 \n", "0 0.496391 0.003181 0.000000 0.392153 0.115440 4.174741 \n", "\n", " Gini \n", "0 0.987317 \n", "0 0.991139 \n", "0 0.908346 \n", "0 0.877999 \n", "0 0.993420 \n", "0 0.994487 \n", "0 0.995706 \n", "0 0.995669 \n", "0 0.996380 \n", "0 0.965327 " ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dir_path=\"Recommendations generated/ml-100k/\"\n", "super_reactions=[4,5]\n", "test=pd.read_csv('./Datasets/ml-100k/test.csv', sep='\\t', header=None)\n", "\n", "ev.evaluate_all(test, dir_path, super_reactions)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.3" } }, "nbformat": 4, "nbformat_minor": 4 }