Add dataset data storage

.gitignore

@@ -1 +1,4 @@
-data/plays/*.txt
+data/plays/*.txt
+data/plays/*.json
+data/plays/data/*.json
+__pycache__/*

app.py

@@ -60,14 +60,22 @@
 import gradio as gr
 import json
 from game import Semantrix
+from huggingface_hub import CommitScheduler
+import os
+
 
 # File paths for configuration and images
 config_file_path = "config/lang.json"
 logo_path = "config/images/logo.png"
 logo_win_path = "config/images/logo_win.gif"
 condition_config_path = "config/condition.json"
+data_path = "data/plays"
 
-condition_name = "condition_3"
+condition_name = "condition_2"
+# Dynamically determine the condition name based on the folder name
+# folder_name = os.path.basename(os.path.dirname(os.path.abspath(__file__)))
+# condition = folder_name.split("_")[-1][-1]
+# condition_name = "condition_" + condition
 
 lang = "Español"  # Default language
 
@@ -81,6 +89,14 @@ hints_enabled = condition_config[condition_name]["hints"]
 with open(config_file_path, "r") as file:
     Config_full = json.load(file)
 
+scheduler = CommitScheduler(
+    repo_id="Jsevisal/semantrix_data_" + condition_name[-1],
+    repo_type="dataset",
+    folder_path=data_path + "/data",
+    path_in_repo="data",
+    every=10,
+)
+
 lang_conf = 0  # Language configuration flag (0 for Spanish, 1 for English)
 
 # Setting the configuration based on the language flag
@@ -155,30 +171,11 @@ with gr.Blocks() as demo:
     )
 
     # Function to reset the game
-    def reset(difficulty):
+    def reset(reload):
         global Config, game, Menu, model, lang  # Declare global variables to modify them within the function
 
-        # Determine the language based on the input parameter
-        # language = 2 if lang == "English" else 0
-
-        # # # Initialize the game object based on the selected model
-        # # if model == "Word2Vec":
-        # #     game = Semantrix(language, "word2vec")  # Use Word2Vec model
-        # # else:
-        # #     game = Semantrix(
-        # #         language, "SentenceTransformer"
-        # #     )  # Use Sentence Transformers model
-
-        # # Set the configuration and menu based on the selected language
-        # if language == 1:
-        #     Config = Config_full["ENG"]["Game"]
-        #     Menu = Config_full["ENG"]["Menu"]
-        # else:
-        #     Config = Config_full["SPA"]["Game"]
-        #     Menu = Config_full["SPA"]["Menu"]
-
-        # Prepare the game with the selected difficulty level
-        # game.prepare_game(1 if hints_enabled else 4)
+        if reload:
+            game.reset_game()  # Reset the game state
 
         # Define the initial output components for the UI
         output = [
@@ -331,7 +328,7 @@ with gr.Blocks() as demo:
                     gr.Button(Menu["Send"], visible=True, variant="primary"),
                     gr.Radio(label="", visible=False),
                     gr.Textbox(visible=False, label=""),
-                    gr.Button(visible=True, variant="stop"),
+                    gr.Button(visible=False, variant="stop"),
                     gr.Textbox(
                         value="",
                         visible=True,
@@ -447,6 +444,34 @@ with gr.Blocks() as demo:
         # Return the output components
         return output
 
+    def commit_data():
+        session_id = game.get_session_id()
+        session_files = [f for f in os.listdir(data_path) if f.startswith(session_id)]
+        combined_data = []
+
+        for file_name in session_files:
+            with open(os.path.join(data_path, file_name), "r") as file:
+                combined_data.append(json.load(file))
+
+        combined_file_path = os.path.join(data_path + "/data", f"{session_id}.json")
+        with open(combined_file_path, "w") as combined_file:
+            json.dump(combined_data, combined_file, indent=4)
+
+        scheduler.push_to_hub()
+
+        return [
+            gr.Button(visible=False),
+            gr.Textbox(visible=False),
+            gr.Textbox(visible=False),
+            gr.Button(
+                "Rellenar cuestionario",
+                variant="primary",
+                link="https://docs.google.com/forms/d/e/1FAIpQLSd0z8nI4hhOSR83yPIw_bR3KkSt25Lsq0ZXG1pZnkldeoceqA/viewform?usp=pp_url&entry.327829192="
+                + session_id,
+                visible=True,
+            ),
+        ]
+
     # Define the UI layout for the gam
     img = gr.Image(logo_path, height=430, interactive=False, visible=True)
     ranking = gr.Markdown(visible=False)
@@ -463,9 +488,9 @@ with gr.Blocks() as demo:
         give_up = gr.Button("Pista", visible=False)
         reload = gr.Button(Menu["Play_again"], visible=False)
     finish = gr.Button(
-        "Terminar y rellenar cuestionario",
+        "Terminar",
         variant="stop",
-        link="https://docs.google.com/forms/d/e/1FAIpQLSd0z8nI4hhOSR83yPIw_bR3KkSt25Lsq0ZXG1pZnkldeoceqA/viewform?usp=pp_url&entry.327829192=Condici%C3%B3n+3",
+        # link="https://docs.google.com/forms/d/e/1FAIpQLSd0z8nI4hhOSR83yPIw_bR3KkSt25Lsq0ZXG1pZnkldeoceqA/viewform?usp=pp_url&entry.327829192=Condici%C3%B3n+0",
         visible=False,
     )
 
@@ -483,16 +508,17 @@ with gr.Blocks() as demo:
         outputs=[state, inp],
     )
     radio.input(change, inputs=[state, inp], outputs=[state, inp])
-
-    # Define events that trigger the game reset
+    finish.click(
+        commit_data, outputs=[reload, out, hint_out, finish]
+    )  # Define events that trigger the game reset
     reload.click(
         reset,
-        inputs=[difficulty],
+        inputs=[gr.State(False)],
         outputs=[state, out, inp, img, but, radio, hint_out, reload, header, finish],
     )
     demo.load(
         reset,
-        inputs=[difficulty],
+        inputs=[gr.State(True)],
         outputs=[state, out, inp, img, but, radio, hint_out, reload, header, finish],
     )
 

game.py

@@ -37,8 +37,10 @@
 # """
 
 import json
+import uuid
 import random
 from datetime import datetime
+import time
 from tqdm import tqdm
 import numpy as np
 from gensim.models import KeyedVectors
@@ -80,6 +82,8 @@ class Semantrix:
         # Set the language of the game
         self.lang = lang
 
+        self.session_id = str(uuid.uuid4().hex)
+
         # Set the model type
         self.model_type = model_type
 
@@ -94,6 +98,8 @@ class Semantrix:
                 )
             self.Config = self.DictWrapper(self.Config_full["ENG"]["Game"])
             self.secret_dict = self.secret["ENG"]
+            self.secret_dict = self.secret["ENG"]
+            self.secret_list = self.secret_dict["basic"]
         else:
             if self.model_type == "word2vec":
                 self.model = KeyedVectors.load(
@@ -106,6 +112,7 @@ class Semantrix:
 
             self.Config = self.DictWrapper(self.Config_full["SPA"]["Game"])
             self.secret_dict = self.secret["SPA"]
+            self.secret_list = self.secret_dict["basic"]
 
         self.model_st = SentenceTransformer(
             "sentence-transformers/paraphrase-multilingual-mpnet-base-v2"
@@ -115,22 +122,23 @@ class Semantrix:
         with open(self.data_path + "ranking.txt", "w+") as file:
             file.write("---------------------------")
 
+    def reset_game(self):
+        self.session_id = str(uuid.uuid4().hex)
+        # Load the secret file where the secret words are stored
+        with open(self.secret_file_path, "r") as file:
+            self.secret = json.load(file)
+        self.secret_dict = self.secret["SPA"]
+        self.secret_list = self.secret_dict["basic"]
+
     # Define the function to prepare the game with the selected difficulty
     def prepare_game(self, difficulty):
 
         # Set the secret list depending on the difficulty
-        # self.secret_list = (
-        #     self.secret_dict["basic"]
-        #     if difficulty <= 2
-        #     else self.secret_dict["advanced"]
-        # )
-        self.secret_list = self.secret_dict["basic"]
-
-        # Select a random secret word from the secret list
-        # self.secret = self.secret_list.pop(random.randint(0, len(self.secret_list) - 1))
         self.secret = self.secret_list.pop(0)
         self.secret = self.secret.lower()
 
+        self.init_time = time.time()
+
         # Store the secret word in the words list
         self.words = [self.Config.secret_word]
 
@@ -298,17 +306,6 @@ class Semantrix:
         # Add the ranking file to the feedback message
         feedback += "[rank]" + open(self.data_path + "ranking.txt", "r").read()
 
-        # Save the ranking file with the plays of the user if the user wins
-        if self.win:
-
-            with open(self.data_path + "ranking.txt", "r") as original_file:
-                file_content = original_file.readlines()
-
-            new_file_name = self.secret + "_" + str(datetime.now()) + ".txt"
-
-            with open(self.data_path + "plays/" + new_file_name, "w+") as new_file:
-                new_file.writelines(file_content[2:])
-
         # Return the feedback message
         return feedback
 
@@ -325,5 +322,25 @@ class Semantrix:
             ),
         )
 
+        # Save the ranking file with the plays of the user if the user wins
+        with open(self.data_path + "ranking.txt", "r") as original_file:
+            file_content = original_file.readlines()[2:]
+            new_file_name = f"{self.session_id}-{self.secret}.json"
+            play_data = {
+                "session_id": self.session_id,
+                "datetime": str(datetime.now()),
+                "time": time.time() - self.init_time,
+                "data": file_content,
+                "win": self.win,
+                "secret": self.secret,
+                "number_of_hints": self.n,
+            }
+
+            with open(self.data_path + "plays/" + new_file_name, "w") as new_file:
+                json.dump(play_data, new_file, indent=4)
+
         # Return the feedback message
         return feedback
+
+    def get_session_id(self):
+        return self.session_id

requirements.txt

@@ -4,4 +4,5 @@ openai==1.2.3
 gradio==5.1.0
 transformers==4.33.2
 huggingface-hub==0.25.2
-python-multipart==0.0.12
+python-multipart==0.0.12
+httpx==0.27.2