Merge branch 'dev' into develop

Author: VincentAuriau

.gitignore

@@ -173,4 +173,4 @@ cython_debug/
 # PyPI configuration file
 .pypirc
 
-.DS_Store
+.DS_Store

doc/laurel_carta.png

@@ -0,0 +1,237 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "60b9cc4f",
+   "metadata": {},
+   "source": [
+    "# Synthetic Experiments"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "984f8af4",
+   "metadata": {},
+   "source": [
+    "## Sample synthetic data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d8f8d31b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sys\n",
+    "sys.path.append(\"../\")\n",
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "\n",
+    "import choice_learn\n",
+    "from python.data import SyntheticDataGenerator\n",
+    "from choice_learn.basket_models import Trip, TripDataset"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b3024007",
+   "metadata": {},
+   "source": [
+    "## Sample purchased baskets"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ed8a74e6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "items_nests = {0:[0, 1, 2],\n",
+    "1: [3, 4, 5],\n",
+    "2: [6],\n",
+    "3: [7]}\n",
+    "\n",
+    "nests_interactions = [[\"\", \"compl\", \"neutral\", \"neutral\"],\n",
+    "[\"compl\", \"\", \"neutral\", \"neutral\"],\n",
+    "[\"neutral\", \"neutral\", \"\", \"neutral\"],\n",
+    "[\"neutral\", \"neutral\", \"neutral\", \"\"]]\n",
+    "\n",
+    "data_gen = SyntheticDataGenerator(items_nest=items_nests, nests_interactions=nests_interactions)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9c3f06eb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dataset = data_gen.generate_dataset(n_baskets=1000)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "51791e7e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "trip_list = []\n",
+    "for basket in dataset:\n",
+    "    trip_list.append(Trip(purchases=basket, prices=np.zeros((8, )), assortment=0))\n",
+    "\n",
+    "trip_dataset = TripDataset(trips=trip_list, available_items=np.ones((1, 8)))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "52b4b18c",
+   "metadata": {},
+   "source": [
+    "## Modelling "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3d6c32e2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from choice_learn.basket_models import AleaCarta"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6ef517b6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "latent_sizes = {\"preferences\": 6, \"price\": 3, \"season\": 3}\n",
+    "n_negative_samples = 2\n",
+    "optimizer = \"adam\"\n",
+    "lr = 1e-2\n",
+    "epochs = 200\n",
+    "batch_size = 32\n",
+    "\n",
+    "model = AleaCarta(\n",
+    "    item_intercept=False,\n",
+    "    price_effects=False,\n",
+    "    seasonal_effects=False,\n",
+    "    latent_sizes=latent_sizes,\n",
+    "    n_negative_samples=n_negative_samples,\n",
+    "    optimizer=optimizer,\n",
+    "    lr=lr,\n",
+    "    epochs=epochs,\n",
+    "    batch_size=batch_size,\n",
+    ")\n",
+    "\n",
+    "model.instantiate(n_items=8, n_stores=2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2f8a915e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "history = model.fit(trip_dataset)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1c78ef41",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.plot(history[\"train_loss\"])\n",
+    "plt.xlabel(\"Epoch\")\n",
+    "plt.ylabel(\"Training Loss\")\n",
+    "plt.legend()\n",
+    "plt.title(\"Training of Shopper\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f337217b",
+   "metadata": {},
+   "source": [
+    "## Results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e4008d65",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "import matplotlib as mpl\n",
+    "import numpy as np\n",
+    "\n",
+    "fig, axes = plt.subplots(nrows=1, ncols=1, figsize=(5, 5))\n",
+    "mask = np.ones((8,8), dtype=bool)\n",
+    "res = []\n",
+    "for i in range(8):\n",
+    "        r = model.compute_batch_utility(item_batch=np.array(list(range(8))),\n",
+    "                basket_batch=np.array([[i] for _ in range(8)]) ,\n",
+    "                store_batch=np.array([0, 0, 0, 0, 0, 0, 0, 0]),\n",
+    "                week_batch=np.array([0, 0, 0, 0, 0, 0, 0, 0]),\n",
+    "                price_batch=np.array([[0, 0, 0, 0, 0, 0] for _ in range(8)]))\n",
+    "        m = np.ones(8)\n",
+    "        m[i] = 0\n",
+    "        den = np.exp(r) * m\n",
+    "        r = den / den.sum()\n",
+    "        # r = np.concatenate([tf.nn.softmax(np.concatenate([r[:i], r[i+1:]]))[:i], [.0], tf.nn.softmax(np.concatenate([r[:i], r[i+1:]]))[i:]])\n",
+    "        res.append(r)\n",
+    "        mask[i][i] = False\n",
+    "\n",
+    "res = np.stack(res)\n",
+    "mask = np.ma.masked_where(mask, res)\n",
+    "\n",
+    "axes.set_xticks([], [])\n",
+    "axes.set_yticks([], [])\n",
+    "im = axes.imshow(np.stack(res), cmap=\"Spectral\", alpha=0.99, vmin=0, vmax=1)\n",
+    "axes.imshow(mask, cmap=mpl.colors.ListedColormap(['white']), alpha=1)\n",
+    "\n",
+    "cbar_ax = fig.add_axes([0.92, 0.15, 0.02, 0.69])\n",
+    "fig.colorbar(im, cax=cbar_ax)\n",
+    "axes.set_title(\"Estimated Conditional Probabilities\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1089cdb5",
+   "metadata": {},
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "with_choice_learn",
+   "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": "3.12.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

doc/resized_img.png

@@ -0,0 +1,79 @@
+"""Data generation related stuff."""
+
+import numpy as np
+from tqdm import trange
+
+
+class SyntheticDataGenerator:
+    def __init__(
+        self,
+        items_nest: dict, # keys should be integer: the nest number
+        nests_interactions: list,
+        proba_complementary_items: float = 0.7,
+        proba_neutral_items: float = 0.15,
+        noise_proba: float = 0.05,
+    ) -> None:
+
+        self.proba_complementary_items = proba_complementary_items
+        self.proba_neutral_items = proba_neutral_items
+        self.noise_proba = noise_proba
+        
+  
+        self.items_nest = items_nest
+        self.nests_interactions = nests_interactions
+
+    def generate_basket(self) -> list:
+        """Generates a basket of items based on the defined item sets and their relations."""
+
+
+        def select_first_item() -> tuple:
+            """Selects the first item and its nest randomly from the available sets."""
+
+            chosen_nest = np.random.choice(list(self.items_nest.keys()))
+            chosen_item = np.random.choice(list(self.items_nest[chosen_nest]))
+            return chosen_item, chosen_nest
+
+        def complete_basket(first_item: int, first_nest: str) -> list:
+            """Completes the basket by adding items based on the relations of the first item."""
+            basket = [first_item]
+            relations = self.nests_interactions[first_nest]
+            for nest_id, items in self.items_nest.items():
+                if (
+                    relations[nest_id] == "compl"
+                    and np.random.random() < self.proba_complementary_items
+                ):
+                    basket.append(np.random.choice(items))
+                elif (
+                    relations[nest_id] == "neutral"
+                    and np.random.random() < self.proba_neutral_items
+                ):
+                    basket.append(np.random.choice(items))
+            return basket
+
+        def add_noise(basket: list) -> list:
+            """Adds noise items to the basket based on the defined noise probability."""
+            if np.random.random() < self.noise_proba:
+                possible_noisy_items = []
+                for nest, items in self.items_nest.items():
+                    for item in items:
+                        if item not in basket:
+                            possible_noisy_items.append(item)
+                if len(possible_noisy_items) > 0:
+                    basket.append(np.random.choice(possible_noisy_items))
+            return basket
+
+        first_chosen_item, first_chosen_nest = select_first_item()
+        basket = complete_basket(first_item=first_chosen_item, first_nest=first_chosen_nest)
+        basket = add_noise(basket)
+
+        return basket
+
+    def generate_dataset(self, n_baskets) -> np.ndarray:
+        """Generates a dataset of baskets."""
+
+        baskets = []
+        for _ in range(n_baskets):
+            baskets.append(self.generate_basket())
+        return np.array(baskets, dtype=object)
+    
+    

doc/rs_img.png

@@ -1,2 +1,2 @@
 choice-learn
-matplotlib
+matplotlib