From c9847b3f41c04ddc181ad204561641237f46c0fa Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Thu, 4 Sep 2025 14:36:07 +0900
Subject: [PATCH 01/26] nah need to rewrite later ugh

---
 README.md | 67 -------------------------------------------------------
 1 file changed, 67 deletions(-)

diff --git a/README.md b/README.md
index ecb74e7..b9b33eb 100644
--- a/README.md
+++ b/README.md
@@ -1,68 +1 @@
 # Multi-Modal-Image-Sentiment-Analysis
-Final Year Project
-
-Python version used : 3.6.0
-
-# To perform Sentiment Analysis of Text present in Image.
-> python3 OCRSentiment.py
-# Face classification and detection.
-Real-time face detection and emotion/gender classification using fer2013/IMDB datasets with a keras CNN model and openCV.
-* IMDB gender classification test accuracy: 96%.
-* fer2013 emotion classification test accuracy: 66%.
-
-
-### Run real-time emotion demo:
-> python3 video_emotion_color_demo.py
-
-### Make inference on single images:
-> python3 image_emotion_gender_demo.py <image_path>
-
-e.g.
-
-> python3 image_emotion_gender_demo.py ../images/test_image.jpg
-
-### Steps to run the final application UI.exe
-Steps to run project:-
-Step 1:- Download project from https://github.com/AnkurKarmakar/Multi-Modal-Image-Sentiment-Analysis
-Extract the zip folder and place the entire project folder in any drive except C drive.
-
-
-Step 2:- Install Python 3.6.0 64 bit from https://www.python.org/downloads/release/python-360/(Note:- Other versions will cause problems with the tensorflow version used)
-
-
-Step 3:- Download site-packages.rar from https://drive.google.com/file/d/1yBVfiMuq6DI8gIF4z__E_gCmwSwEL4uu/view?usp=sharing and extract it into C:\Users\<UserName>\AppData\Local\Programs\Python\Python36\Lib\
-
-
-Step 4:- Go to project folder where requirements.txt is present.Then open cmd there and type pip install -r requirements.txt
-
-
-Step 5:- Download Tesseract from https://sourceforge.net/projects/tesseract-ocr-alt/files/tesseract-ocr-setup-3.02.02.exe/download  and then install it
-
-
-Step 6:- Go to project folder. Inside src folder there is UI.exe. Run it and program will run. After the UI pops up click on Browse to select image and then click on Analyze.
-
-
-### To train previous/new models for emotion classification:
-
-
-* Download the fer2013.tar.gz file from [here](https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge/data)
-
-* Move the downloaded file to the datasets directory inside this repository.
-
-* Untar the file:
-> tar -xzf fer2013.tar
-
-* Run the train_emotion_classification.py file
-> python3 train_emotion_classifier.py
-
-### To train previous/new models for gender classification:
-
-* Download the imdb_crop.tar file from [here](https://data.vision.ee.ethz.ch/cvl/rrothe/imdb-wiki/) (It's the 7GB button with the tittle Download faces only).
-
-* Move the downloaded file to the datasets directory inside this repository.
-
-* Untar the file:
-> tar -xfv imdb_crop.tar
-
-* Run the train_gender_classification.py file
-> python3 train_gender_classifier.py

From 59915ab3ce230844dcda42a86b69b2ccc19f1f73 Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Thu, 4 Sep 2025 14:36:39 +0900
Subject: [PATCH 02/26] new datasaet on onigiri code

---
 src/utils/datasets.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/src/utils/datasets.py b/src/utils/datasets.py
index aa445a7..d133227 100644
--- a/src/utils/datasets.py
+++ b/src/utils/datasets.py
@@ -21,6 +21,8 @@ def __init__(self, dataset_name='imdb',
             self.dataset_path = '../datasets/imdb_crop/imdb.mat'
         elif self.dataset_name == 'fer2013':
             self.dataset_path = '../datasets/fer2013/fer2013.csv'
+        elif self.dataset_name == 'onigiri':
+            self.dataset_path = '../datasets/onigiri/sfj_weir_392834.csv'
         elif self.dataset_name == 'KDEF':
             self.dataset_path = '../datasets/KDEF/'
         else:

From 4beb9236acd307eaf8c9d3660a88a7dade13d523 Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Thu, 4 Sep 2025 14:37:16 +0900
Subject: [PATCH 03/26] new modle for onigiri

---
 src/models/cnn.py | 78 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 78 insertions(+)

diff --git a/src/models/cnn.py b/src/models/cnn.py
index cbdbb08..6ce1b0a 100644
--- a/src/models/cnn.py
+++ b/src/models/cnn.py
@@ -9,6 +9,7 @@
 from keras.layers import SeparableConv2D
 from keras import layers
 from keras.regularizers import l2
+import tensorflow as tf
 
 
 def simple_CNN(input_shape, num_classes):
@@ -345,6 +346,83 @@ def big_XCEPTION(input_shape, num_classes):
     return model
 
 
+def model_allofasudden_that_uses_tensorflow(
+    sequence_length,
+    face_front_pixel,
+    face_back_pixel,
+    in_channels,
+    out_features,
+    number_of_conv3d_layers,
+    num_weather_types,
+    conv3d_channels=32,
+    fc_features=128,
+    spatial_kernel_size=3,
+    temporal_kernel_size=3,
+):
+    """
+    Multimodal 데이터를 인코딩하는 3D CNN 기반의 신경망 모델을 생성하는 함수
+
+    여러 시계열 데이터를 Conv3D 레이어를 통해 특징을 추출한 후, Fully Connected 레이어를 통해
+    압축된 feature representation을 생성한다
+
+    :param int sequence_length: 입력 데이터의 시간 sequence 길이
+    :param int face_front_pixel: 입력 데이터의 위도 방향 픽셀 수
+    :param int face_back_pixel: 입력 데이터의 경도 방향 픽셀 수
+    :param int in_channels: 입력 데이터의 채널 수
+    :param int out_features: 최종 출력 feature 크기
+    :param int number_of_conv3d_layers: 사용할 Conv3D 레이어 개수
+    :param int conv3d_channels: Conv3D 필터 개수 (기본값: 32)
+    :param int fc_features: Fully Connected layer에서 사용할 hidden feature 크기 (기본값: 128)
+    :param int spatial_kernel_size: Conv3D에서 사용할 Spatial 차원의 커널 크기 (기본값: 3)
+    :param int temporal_kernel_size: Conv3D에서 사용할 Temporal 차원의 커널 크기 (기본값: 3)
+
+    :return: Multimodal 데이터를 처리하는 3D CNN 기반의 Keras 모델.
+    :rtype: tf.keras.Model
+    """
+
+    # Inputs
+    data_input = tf.keras.Input(
+        shape=(sequence_length, face_front_pixel, face_back_pixel, in_channels),
+        name="data_input"
+    )
+    site_id_input = tf.keras.Input(
+        shape=(), dtype=tf.int32, name="site_id"
+    )
+
+    # weather embedding: shape = (batch, 1, H, W, 1)
+    weather_embedding = tf.keras.layers.Embedding(
+        input_dim=num_weather_types,
+        output_dim=face_front_pixel * face_back_pixel
+    )(site_id_input)
+    weather_map = tf.keras.layers.Reshape((1, face_front_pixel, face_back_pixel, 1))(weather_embedding)
+    weather_map = tf.keras.layers.Lambda(
+        lambda x: tf.tile(x, [1, sequence_length, 1, 1, 1])
+    )(weather_map)
+
+    # Concatenate weather map as additional channel
+    x = tf.keras.layers.Concatenate(axis=-1)([data_input, weather_map])
+
+    # Initial Conv3D Block
+    for _ in range(number_of_conv3d_layers):
+        x = tf.keras.layers.ZeroPadding3D(padding=((1, 1), (0, 0), (0, 0)))(x)  # pad time only
+        x = tf.keras.layers.Conv3D(
+            filters=conv3d_channels,
+            kernel_size=(temporal_kernel_size, spatial_kernel_size, spatial_kernel_size),
+            strides=(1, 1, 1),
+            padding="valid"  # spatial dims shrink
+        )(x)
+        x = tf.keras.layers.ELU()(x)
+
+    # Flatten + FC
+    x = tf.keras.layers.Flatten()(x)
+    x = tf.keras.layers.Dense(fc_features, activation="elu")(x)
+    outputs = tf.keras.layers.Dense(out_features, activation="elu")(x)
+
+    model = tf.keras.Model(inputs=[data_input, site_id_input], outputs=outputs)
+    return model
+
+
+
 if __name__ == "__main__":
     input_shape = (64, 64, 1)
     num_classes = 7

From 7df0073f9c8236008ad2b3329d5c3a53779d2414 Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Thu, 4 Sep 2025 14:37:45 +0900
Subject: [PATCH 04/26] new module to data process the new onigiri

---
 .../separate_date_articulator_that_is_new.py  | 94 +++++++++++++++++++
 1 file changed, 94 insertions(+)
 create mode 100644 src/utils/separate_date_articulator_that_is_new.py

diff --git a/src/utils/separate_date_articulator_that_is_new.py b/src/utils/separate_date_articulator_that_is_new.py
new file mode 100644
index 0000000..1cc0222
--- /dev/null
+++ b/src/utils/separate_date_articulator_that_is_new.py
@@ -0,0 +1,94 @@
+from dasenima import SelectDateSpatialSlice, base_and_issue_time_declaration, generate_hourly_timestep  # needs pip install dasenima separately from our company file!!
+from utils.datasets import DataManager
+from datetime import timedelta, datetime
+import numpy as np
+
+date_spatial_slice = SelectDateSpatialSlice()
+def accumulated_value_update(var_name, df):
+    """
+    주어진 변수(var_name)에 대한 변화량을 계산하여 '_delta' 컬럼을 추가함.
+    매개변수:
+    - var_name (str): 변화량을 계산할 변수명.
+    - df (pd.DataFrame): 변환을 수행할 데이터프레임.
+    반환값:
+    - pd.DataFrame: 변화량이 반영된 데이터프레임.
+    """
+
+    var_name_delta = var_name + "_delta"
+    df[var_name_delta] = (df[var_name].shift(-1) - df[var_name]).fillna(0)
+    df[var_name_delta] = np.where(df["leadtime"] == 9000, 0, df[var_name_delta])
+
+    return df
+
+def selected_time_slice(chosen_t0, df_weatherMood):
+    (
+        basetime_t0_hr_int,
+        issued_time_hr_int,
+        issued_date_date_int,
+        issued_month_int,
+        issued_time_hr_str,
+    ) = base_and_issue_time_declaration(chosen_t0)
+
+    # up until here, issued-date and hour is matched
+    df_weatherMood_issueddate_all_filtered_cleanly = df_weatherMood[
+        (df_weatherMood.issueddate == str(issued_date_date_int))
+        & (df_weatherMood.issuedhour == issued_time_hr_str)
+    ].reset_index(drop=True)
+
+    time_slice_index_t0 = df_weatherMood_issueddate_all_filtered_cleanly[
+        (df_weatherMood_issueddate_all_filtered_cleanly.basetime == chosen_t0)
+    ].index[0]
+
+    df_weatherMood_issueddate_all_filtered_cleanly = df_weatherMood_issueddate_all_filtered_cleanly.iloc[
+        time_slice_index_t0 - 2 : time_slice_index_t0 + 9
+    ]
+
+    return df_weatherMood_issueddate_all_filtered_cleanly
+
+
+def return_emotions_mood_weather_mixer_combinations(df, batch_size,num_epochs,patience ):
+    sroe_code_values = df[batch_size+"_"+num_epochs+"_"+patience]
+    mood_types = df[batch_size+"_"+"mood"].unique()
+    weather_types = df[batch_size+"_"+"weather"].unique()
+    start = sroe_code_values // 100
+    end   = sroe_code_values // 10
+
+    regional_coords = date_spatial_slice(sroe_code_values)
+    timestamps = generate_hourly_timestep(start, end)
+
+    combined = [
+        [mood, weather, codeNum]
+        for codeNum in sroe_code_values
+        for mood in mood_types
+        for weather in weather_types
+    ]
+
+    all_timesteps = generate_monthly_timestamps(start, end)
+
+    return combined, all_timesteps
+
+def generate_monthly_timestamps(start_timestamp, end_timestamp):
+    # datetime 으로 변환
+    start_date = datetime.strptime(start_timestamp, "%Y%m%d%H")
+    end_date = datetime.strptime(end_timestamp, "%Y%m%d%H")
+
+    # 각 개월 수 마다로
+    monthly_timestamps = {}
+
+    # 각 매시간 (everyhour) 루핑
+    current_time = start_date
+    while current_time <= end_date:
+        month_key = current_time.strftime("%Y%m")  #  YYYYMM
+        timestamp_int = int(current_time.strftime("%Y%m%d%H%M%S"))  # YYYMMDDHHMMSS
+
+        # 해당 달이 새로 시작되면, dict에 새로운 키를 만든다
+        if month_key not in monthly_timestamps:
+            monthly_timestamps[month_key] = []
+
+        # 해당 알맞는 개월 key에 element로 Dict에 포함
+        monthly_timestamps[month_key].append(timestamp_int)
+
+        # 아음 시간으로
+        current_time += timedelta(hours=1)
+
+    return monthly_timestamps
\ No newline at end of file

From ecdab55a6259986f90f029c8da1739351dc9d647 Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Thu, 4 Sep 2025 14:51:01 +0900
Subject: [PATCH 05/26] to fit the new value

---
 src/train_gender_classifier.py                | 70 ++++++++++++++++++-
 .../separate_date_articulator_that_is_new.py  |  6 +-
 2 files changed, 71 insertions(+), 5 deletions(-)

diff --git a/src/train_gender_classifier.py b/src/train_gender_classifier.py
index df5fc8d..e9c867c 100644
--- a/src/train_gender_classifier.py
+++ b/src/train_gender_classifier.py
@@ -1,9 +1,10 @@
-
-
+import numpy as np
+import pandas as pd
+from utils.separate_date_articulator_that_is_new import return_emotions_mood_weather_mixer_combinations
 from keras.callbacks import CSVLogger, ModelCheckpoint, EarlyStopping
 from keras.callbacks import ReduceLROnPlateau
 from utils.datasets import DataManager
-from models.cnn import mini_XCEPTION
+from models.cnn import mini_XCEPTION, model_allofasudden_that_uses_tensorflow
 from utils.data_augmentation import ImageGenerator
 from utils.datasets import split_imdb_data
 
@@ -36,6 +37,69 @@
                                  grayscale=grayscale,
                                  do_random_crop=do_random_crop)
 
+# onigiri - as of 2025
+df_weather_mood = DataManager("onigiri")
+all_possible_combinations_input, y_true = return_emotions_mood_weather_mixer_combinations(df_weather_mood, batch_size,num_epochs,patience)
+all_possible_combinations_input = all_possible_combinations_input.to_numpy()
+y_true = y_true.to_numpy()
+
+mood_model = model_allofasudden_that_uses_tensorflow(
+    sequence_length=all_possible_combinations_input.shape[1],
+    face_front_pixel=all_possible_combinations_input.shape[2],
+    face_back_pixel=all_possible_combinations_input.shape[3],
+    in_channels=all_possible_combinations_input.shape[4],
+    out_features=y_true.shape[1] if y_true.ndim > 1 else 1,
+    number_of_conv3d_layers=3,
+    num_weather_types=10,
+    conv3d_channels=32,
+    fc_features=128,
+    spatial_kernel_size=3,
+    temporal_kernel_size=3
+)
+
+mood_model.compile(
+    optimizer="adam",
+    loss="categorical_crossentropy",
+    metrics=["mae"]
+)
+
+mood_model.summary()
+
+# ---- 3) Callbacks (match the style from your example) ----
+# fill these in (same variable names you used before)
+patience = 10
+log_file_path = "mood_train_log.csv"
+trained_models_path = "checkpoints/cnn3d_gsp"  # no extension; we'll format epochs/metrics into the filename
+
+early_stop = EarlyStopping(monitor="val_loss", patience=patience, restore_best_weights=True)
+reduce_lr = ReduceLROnPlateau(monitor="val_loss", factor=0.1, patience=max(1, patience // 2), verbose=1)
+csv_logger = CSVLogger(log_file_path, append=False)
+
+# For TF 2.x, use metric names you actually log; here we use val_mae since it's in metrics.
+# If you prefer val_loss, change the format accordingly.
+model_names = trained_models_path + ".onigiri_df2j3i_dif982183nfdsfuh982h312jkhkdsahbadyfgasdfr234.hdf5"
+model_checkpoint = ModelCheckpoint(
+    filepath=model_names,
+    monitor="val_loss",
+    verbose=1,
+    save_best_only=True,
+    save_weights_only=False
+)
+
+callbacks = [model_checkpoint, csv_logger, early_stop, reduce_lr]
+
+# ---- 4A) Fit with arrays / tf.data (recommended) ----
+history = mood_model.fit(
+    all_possible_combinations_input, y_true,
+    epochs=num_epochs,
+    batch_size=batch_size,
+    validation_split=0.2,
+    callbacks=callbacks,
+    verbose=1
+)
+
+
+
 # model parameters/compilation
 model = mini_XCEPTION(input_shape, num_classes)
 model.compile(optimizer='adam',
diff --git a/src/utils/separate_date_articulator_that_is_new.py b/src/utils/separate_date_articulator_that_is_new.py
index 1cc0222..8dff606 100644
--- a/src/utils/separate_date_articulator_that_is_new.py
+++ b/src/utils/separate_date_articulator_that_is_new.py
@@ -20,7 +20,8 @@ def accumulated_value_update(var_name, df):
 
     return df
 
-def selected_time_slice(chosen_t0, df_weatherMood):
+def selected_time_slice(df_weatherMood):
+    chosen_t0 = df_weatherMood["chosen_t0"][9000]
     (
         basetime_t0_hr_int,
         issued_time_hr_int,
@@ -46,7 +47,8 @@ def selected_time_slice(chosen_t0, df_weatherMood):
     return df_weatherMood_issueddate_all_filtered_cleanly
 
 
-def return_emotions_mood_weather_mixer_combinations(df, batch_size,num_epochs,patience ):
+def return_emotions_mood_weather_mixer_combinations(df_weatherMood, batch_size,num_epochs,patience ):
+    df = selected_time_slice(df_weatherMood)
     sroe_code_values = df[batch_size+"_"+num_epochs+"_"+patience]
     mood_types = df[batch_size+"_"+"mood"].unique()
     weather_types = df[batch_size+"_"+"weather"].unique()

From 0ebf6311437c2fd26da6816ad0566131399b613a Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Thu, 4 Sep 2025 14:55:37 +0900
Subject: [PATCH 06/26] predict and implement the result

---
 src/image_emotion_gender_demo.py | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/src/image_emotion_gender_demo.py b/src/image_emotion_gender_demo.py
index 684d236..056968c 100644
--- a/src/image_emotion_gender_demo.py
+++ b/src/image_emotion_gender_demo.py
@@ -18,6 +18,7 @@
 detection_model_path = '../trained_models/detection_models/haarcascade_frontalface_default.xml'
 emotion_model_path = '../trained_models/emotion_models/fer2013_mini_XCEPTION.102-0.66.hdf5'
 gender_model_path = '../trained_models/gender_models/simple_CNN.81-0.96.hdf5'
+onigiri_model_path = '../trained_models/onigiri_models/onigiri_df2j3i_dif982183nfdsfuh982h312jkhkdsahbadyfgasdfr234.hdf5'
 emotion_labels = get_labels('fer2013')
 gender_labels = get_labels('imdb')
 font = cv2.FONT_HERSHEY_SIMPLEX
@@ -27,15 +28,18 @@
 gender_offsets = (10, 10)
 emotion_offsets = (20, 40)
 emotion_offsets = (0, 0)
+mood_offsets = (5, 9)
 
 # loading models
 face_detection = load_detection_model(detection_model_path)
 emotion_classifier = load_model(emotion_model_path, compile=False)
 gender_classifier = load_model(gender_model_path, compile=False)
+mood_classifier   = load_model(onigiri_model_path, compile=False)
 
 # getting input model shapes for inference
 emotion_target_size = emotion_classifier.input_shape[1:3]
 gender_target_size = gender_classifier.input_shape[1:3]
+mood_target_size = mood_classifier.input_shape[1:3]
 
 # loading images
 rgb_image = load_image(image_path, grayscale=False)
@@ -48,11 +52,15 @@
     x1, x2, y1, y2 = apply_offsets(face_coordinates, gender_offsets)
     rgb_face = rgb_image[y1:y2, x1:x2]
 
+    x1, x2, y1, y2 = apply_offsets(face_coordinates, mood_offsets)
+    moody_face = rgb_image[y1:y2, x1:x2]   # uses the same rgb_face since mood comes from face
+
     x1, x2, y1, y2 = apply_offsets(face_coordinates, emotion_offsets)
     gray_face = gray_image[y1:y2, x1:x2]
 
     try:
         rgb_face = cv2.resize(rgb_face, (gender_target_size))
+        moody_face = cv2.resize(moody_face, (mood_target_size))
         gray_face = cv2.resize(gray_face, (emotion_target_size))
     except:
         continue
@@ -67,7 +75,9 @@
     gray_face = np.expand_dims(gray_face, 0)
     gray_face = np.expand_dims(gray_face, -1)
     emotion_label_arg = np.argmax(emotion_classifier.predict(gray_face))
+    mood_label_arg = np.argmax(mood_classifier.predict(moody_face))
     emotion_text = emotion_labels[emotion_label_arg]
+    mood_text = emotion_labels[mood_label_arg]
 
     if gender_text == gender_labels[0]:
         color = (0, 0, 255)
@@ -77,6 +87,7 @@
     draw_bounding_box(face_coordinates, rgb_image, color)
     draw_text(face_coordinates, rgb_image, gender_text, color, 0, -20, 1, 2)
     draw_text(face_coordinates, rgb_image, emotion_text, color, 0, -50, 1, 2)
+    draw_text(face_coordinates, rgb_image, mood_text, color, 0, -35, 1, 2)
 
 bgr_image = cv2.cvtColor(rgb_image, cv2.COLOR_RGB2BGR)
 cv2.imwrite('../images/predicted_test_image.png', bgr_image)

From 74e09dd4c83d4fed8603c881003acfa65c29568b Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Thu, 4 Sep 2025 15:17:51 +0900
Subject: [PATCH 07/26] wrote github copilot instruction by markdown

---
 .github/copilot-instructions.md | 58 +++++++++++++++++++++++++++++++++
 1 file changed, 58 insertions(+)
 create mode 100644 .github/copilot-instructions.md

diff --git a/.github/copilot-instructions.md b/.github/copilot-instructions.md
new file mode 100644
index 0000000..d2cece9
--- /dev/null
+++ b/.github/copilot-instructions.md
@@ -0,0 +1,58 @@
+description: 'Python coding conventions and guidelines'
+applyTo: '**/*.py'
+---
+
+# Python Coding Conventions
+
+## Python Instructions
+
+- Write clear and concise comments for each function.
+- Ensure functions have descriptive names and include type hints.
+- Provide docstrings following PEP 257 conventions.
+- Use the `typing` module for type annotations (e.g., `List[str]`, `Dict[str, int]`).
+- Break down complex functions into smaller, more manageable functions.
+- Write docstrings and comments primarily in Korean (unless external libraries or public APIs require English).
+
+## General Instructions
+
+- Always prioritize readability and clarity.
+- For algorithm-related code, include explanations of the approach used.
+- Write code with good maintainability practices, including comments on why certain design decisions were made.
+- Handle edge cases and write clear exception handling.
+- For libraries or external dependencies, mention their usage and purpose in comments.
+- Use consistent naming conventions and follow language-specific best practices.
+- Ensure all referenced functions, classes, and variables are properly declared before use.
+- Carefully read and comprehensively understand each function, loop, and conditional (and their combinations); when appropriate, refactor into more efficient one-liners/two-liners or leverage built-in/vectorized methods from `numpy`, `pandas`, `datetime`, `itertools`, etc., while preserving behavior and clarity.
+- Write concise, efficient, and idiomatic code that is also easily understandable.
+
+## Code Style and Formatting
+- Use snake_case for variable and function names. Use CamelCase for class names. Follow PEP 8 style guidelines. Include type hints for function parameters and return types.
+- Follow the **PEP 8** style guide for Python.
+- Maintain proper indentation (use 4 spaces for each level of indentation).
+- Ensure lines do not exceed 79 characters.
+- Place function and class docstrings immediately after the `def` or `class` keyword.
+- Use blank lines to separate functions, classes, and code blocks where appropriate.
+
+## Edge Cases and Testing
+
+- Always include test cases for critical paths of the application.
+- Account for common edge cases like empty inputs, invalid data types, and large datasets.
+- Include comments for edge cases and the expected behavior in those cases.
+- Write unit tests for functions and document them with docstrings explaining the test cases.
+
+## Example of Proper Documentation
+
+```python
+def calculate_area(radius: float) -> float:
+    """
+    원의 면적을 계산하는 함수
+    
+    주어진 반지름(`radius`)을 이용하여 원의 면적을 계산한다. 
+    면적은 π * (반지름^2) 공식을 사용한다.
+    
+    :param float radius: 원의 반지름
+    :return: 원의 면적 값
+    :rtype: float
+    """
+    import math
+    return math.pi * radius ** 2

From e85791b3df15873973277adfa9b5c287a3ff7367 Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Thu, 4 Sep 2025 16:49:02 +0900
Subject: [PATCH 08/26] Update
 src/utils/separate_date_articulator_that_is_new.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---
 src/utils/separate_date_articulator_that_is_new.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/utils/separate_date_articulator_that_is_new.py b/src/utils/separate_date_articulator_that_is_new.py
index 8dff606..fbb98c8 100644
--- a/src/utils/separate_date_articulator_that_is_new.py
+++ b/src/utils/separate_date_articulator_that_is_new.py
@@ -49,9 +49,9 @@ def selected_time_slice(df_weatherMood):
 
 def return_emotions_mood_weather_mixer_combinations(df_weatherMood, batch_size,num_epochs,patience ):
     df = selected_time_slice(df_weatherMood)
-    sroe_code_values = df[batch_size+"_"+num_epochs+"_"+patience]
-    mood_types = df[batch_size+"_"+"mood"].unique()
-    weather_types = df[batch_size+"_"+"weather"].unique()
+    sroe_code_values = df[f"{batch_size}_{num_epochs}_{patience}"]
+    mood_types = df[f"{batch_size}_mood"].unique()
+    weather_types = df[f"{batch_size}_weather"].unique()
     start = sroe_code_values // 100
     end   = sroe_code_values // 10
 

From 982e7aefcb9ba476c2535d3b94b29998f1f05094 Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Thu, 4 Sep 2025 16:52:03 +0900
Subject: [PATCH 09/26] unnecessary comment

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---
 src/utils/separate_date_articulator_that_is_new.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/utils/separate_date_articulator_that_is_new.py b/src/utils/separate_date_articulator_that_is_new.py
index fbb98c8..a672e93 100644
--- a/src/utils/separate_date_articulator_that_is_new.py
+++ b/src/utils/separate_date_articulator_that_is_new.py
@@ -1,4 +1,4 @@
-from dasenima import SelectDateSpatialSlice, base_and_issue_time_declaration, generate_hourly_timestep  # needs pip install dasenima separately from our company file!!
+from dasenima import SelectDateSpatialSlice, base_and_issue_time_declaration, generate_hourly_timestep
 from utils.datasets import DataManager
 from datetime import timedelta, datetime
 import numpy as np

From 4a27990a5b5c50bdce3efbce5c2dd8495e068226 Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Thu, 4 Sep 2025 16:53:54 +0900
Subject: [PATCH 10/26] data type

---
 src/utils/separate_date_articulator_that_is_new.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/utils/separate_date_articulator_that_is_new.py b/src/utils/separate_date_articulator_that_is_new.py
index a672e93..9190efc 100644
--- a/src/utils/separate_date_articulator_that_is_new.py
+++ b/src/utils/separate_date_articulator_that_is_new.py
@@ -65,7 +65,7 @@ def return_emotions_mood_weather_mixer_combinations(df_weatherMood, batch_size,n
         for weather in weather_types
     ]
 
-    all_timesteps = generate_monthly_timestamps(start, end)
+    all_timesteps = generate_monthly_timestamps(str(start), str(end))
 
     return combined, all_timesteps
 

From 5949ee25fce35330f027e83eb0086e88e915049f Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Thu, 4 Sep 2025 16:59:04 +0900
Subject: [PATCH 11/26] list, dict to numpy

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---
 src/train_gender_classifier.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/train_gender_classifier.py b/src/train_gender_classifier.py
index e9c867c..cd6601b 100644
--- a/src/train_gender_classifier.py
+++ b/src/train_gender_classifier.py
@@ -40,8 +40,8 @@
 # onigiri - as of 2025
 df_weather_mood = DataManager("onigiri")
 all_possible_combinations_input, y_true = return_emotions_mood_weather_mixer_combinations(df_weather_mood, batch_size,num_epochs,patience)
-all_possible_combinations_input = all_possible_combinations_input.to_numpy()
-y_true = y_true.to_numpy()
+all_possible_combinations_input = np.array(all_possible_combinations_input)
+y_true = np.array(list(y_true.values())) if isinstance(y_true, dict) else np.array(y_true)
 
 mood_model = model_allofasudden_that_uses_tensorflow(
     sequence_length=all_possible_combinations_input.shape[1],

From a593cb8c3cf89e843907e293fb0b89b4acdcc684 Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Thu, 4 Sep 2025 17:01:38 +0900
Subject: [PATCH 12/26] emotional label

---
 src/image_emotion_gender_demo.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/image_emotion_gender_demo.py b/src/image_emotion_gender_demo.py
index 056968c..e0aae80 100644
--- a/src/image_emotion_gender_demo.py
+++ b/src/image_emotion_gender_demo.py
@@ -77,7 +77,7 @@
     emotion_label_arg = np.argmax(emotion_classifier.predict(gray_face))
     mood_label_arg = np.argmax(mood_classifier.predict(moody_face))
     emotion_text = emotion_labels[emotion_label_arg]
-    mood_text = emotion_labels[mood_label_arg]
+    mood_text = emotion_labels[mood_label_arg]      # must use the same label for specific purposed proven by the journal
 
     if gender_text == gender_labels[0]:
         color = (0, 0, 255)

From 2fa75ece1a5eaa708c39d04cfad6051604f1154a Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Thu, 4 Sep 2025 17:50:29 +0900
Subject: [PATCH 13/26] functional change

---
 src/models/cnn.py | 27 +++++----------------------
 1 file changed, 5 insertions(+), 22 deletions(-)

diff --git a/src/models/cnn.py b/src/models/cnn.py
index 6ce1b0a..ceb00b3 100644
--- a/src/models/cnn.py
+++ b/src/models/cnn.py
@@ -345,7 +345,6 @@ def big_XCEPTION(input_shape, num_classes):
     model = Model(img_input, output)
     return model
 
-
 def model_allofasudden_that_uses_tensorflow(
     sequence_length,
     face_front_pixel,
@@ -353,7 +352,6 @@ def model_allofasudden_that_uses_tensorflow(
     in_channels,
     out_features,
     number_of_conv3d_layers,
-    num_weather_types,
     conv3d_channels=32,
     fc_features=128,
     spatial_kernel_size=3,
@@ -380,36 +378,21 @@ def model_allofasudden_that_uses_tensorflow(
     :rtype: tf.keras.Model
     """
 
-    # Inputs
+    # Only the main input
     data_input = tf.keras.Input(
         shape=(sequence_length, face_front_pixel, face_back_pixel, in_channels),
         name="data_input"
     )
-    site_id_input = tf.keras.Input(
-        shape=(), dtype=tf.int32, name="site_id"
-    )
-
-    # weather embedding: shape = (batch, 1, H, W, 1)
-    weather_embedding = tf.keras.layers.Embedding(
-        input_dim=num_weather_types,
-        output_dim=face_front_pixel * face_back_pixel
-    )(site_id_input)
-    weather_map = tf.keras.layers.Reshape((1, face_front_pixel, face_back_pixel, 1))(weather_embedding)
-    weather_map = tf.keras.layers.Lambda(
-        lambda x: tf.tile(x, [1, sequence_length, 1, 1, 1])
-    )(weather_map)
-
-    # Concatenate weather map as additional channel
-    x = tf.keras.layers.Concatenate(axis=-1)([data_input, weather_map])
 
-    # Initial Conv3D Block
+    # Conv3D stack
+    x = data_input
     for _ in range(number_of_conv3d_layers):
         x = tf.keras.layers.ZeroPadding3D(padding=((1, 1), (0, 0), (0, 0)))(x)  # pad time only
         x = tf.keras.layers.Conv3D(
             filters=conv3d_channels,
             kernel_size=(temporal_kernel_size, spatial_kernel_size, spatial_kernel_size),
             strides=(1, 1, 1),
-            padding="valid"  # spatial dims shrink
+            padding="valid"
         )(x)
         x = tf.keras.layers.ELU()(x)
 
@@ -418,7 +401,7 @@ def model_allofasudden_that_uses_tensorflow(
     x = tf.keras.layers.Dense(fc_features, activation="elu")(x)
     outputs = tf.keras.layers.Dense(out_features, activation="elu")(x)
 
-    model = tf.keras.Model(inputs=[data_input, site_id_input], outputs=outputs)
+    model = tf.keras.Model(inputs=data_input, outputs=outputs)
     return model
 
 

From c0753bcb178337100a365e5906785b2ba913e446 Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Thu, 4 Sep 2025 17:52:07 +0900
Subject: [PATCH 14/26] onigiri --- dataload

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---
 src/train_gender_classifier.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/train_gender_classifier.py b/src/train_gender_classifier.py
index cd6601b..1a4bbf6 100644
--- a/src/train_gender_classifier.py
+++ b/src/train_gender_classifier.py
@@ -38,7 +38,7 @@
                                  do_random_crop=do_random_crop)
 
 # onigiri - as of 2025
-df_weather_mood = DataManager("onigiri")
+df_weather_mood = pd.read_csv('../datasets/onigiri.csv')
 all_possible_combinations_input, y_true = return_emotions_mood_weather_mixer_combinations(df_weather_mood, batch_size,num_epochs,patience)
 all_possible_combinations_input = np.array(all_possible_combinations_input)
 y_true = np.array(list(y_true.values())) if isinstance(y_true, dict) else np.array(y_true)

From 40d98f1def85001c208eb675f0fe172d9599e622 Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Thu, 4 Sep 2025 17:53:22 +0900
Subject: [PATCH 15/26] inputshape debug

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---
 src/image_emotion_gender_demo.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/image_emotion_gender_demo.py b/src/image_emotion_gender_demo.py
index e0aae80..5ac4bff 100644
--- a/src/image_emotion_gender_demo.py
+++ b/src/image_emotion_gender_demo.py
@@ -39,7 +39,7 @@
 # getting input model shapes for inference
 emotion_target_size = emotion_classifier.input_shape[1:3]
 gender_target_size = gender_classifier.input_shape[1:3]
-mood_target_size = mood_classifier.input_shape[1:3]
+mood_target_size = mood_classifier.input_shape[0][1:3]
 
 # loading images
 rgb_image = load_image(image_path, grayscale=False)

From 8d590ed914b94dd601a527aa61b45c8904dce5d9 Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Thu, 4 Sep 2025 17:55:06 +0900
Subject: [PATCH 16/26] commentary

---
 src/image_emotion_gender_demo.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/image_emotion_gender_demo.py b/src/image_emotion_gender_demo.py
index e0aae80..e65d917 100644
--- a/src/image_emotion_gender_demo.py
+++ b/src/image_emotion_gender_demo.py
@@ -77,7 +77,7 @@
     emotion_label_arg = np.argmax(emotion_classifier.predict(gray_face))
     mood_label_arg = np.argmax(mood_classifier.predict(moody_face))
     emotion_text = emotion_labels[emotion_label_arg]
-    mood_text = emotion_labels[mood_label_arg]      # must use the same label for specific purposed proven by the journal
+    mood_text = emotion_labels[mood_label_arg]      # must use the same emotion_labels for specific purposed proven by the journal
 
     if gender_text == gender_labels[0]:
         color = (0, 0, 255)

From 98f1ebd641133fb0c132275f14d40202666d480b Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Fri, 5 Sep 2025 09:54:21 +0900
Subject: [PATCH 17/26] label

---
 src/utils/datasets.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/src/utils/datasets.py b/src/utils/datasets.py
index d133227..a3a3ab3 100644
--- a/src/utils/datasets.py
+++ b/src/utils/datasets.py
@@ -112,6 +112,8 @@ def get_labels(dataset_name):
         return {0: 'woman', 1: 'man'}
     elif dataset_name == 'KDEF':
         return {0: 'AN', 1: 'DI', 2: 'AF', 3: 'HA', 4: 'SA', 5: 'SU', 6: 'NE'}
+    elif dataset_name == 'onigiri':
+        return {0: 'A021', 1: 'JSI', 2: 'SOMD', 11: 'KOBS', 131: 'SSOP'}
     else:
         raise Exception('Invalid dataset name')
 

From 6dcedfc084ca0ad9640ef52726988136a990f3ec Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Fri, 5 Sep 2025 09:57:32 +0900
Subject: [PATCH 18/26] changled label

---
 src/image_emotion_gender_demo.py | 3 ++-
 src/utils/datasets.py            | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/src/image_emotion_gender_demo.py b/src/image_emotion_gender_demo.py
index 324c567..3d28a85 100644
--- a/src/image_emotion_gender_demo.py
+++ b/src/image_emotion_gender_demo.py
@@ -21,6 +21,7 @@
 onigiri_model_path = '../trained_models/onigiri_models/onigiri_df2j3i_dif982183nfdsfuh982h312jkhkdsahbadyfgasdfr234.hdf5'
 emotion_labels = get_labels('fer2013')
 gender_labels = get_labels('imdb')
+mood_labels = get_labels('onigiri')
 font = cv2.FONT_HERSHEY_SIMPLEX
 
 # hyper-parameters for bounding boxes shape
@@ -77,7 +78,7 @@
     emotion_label_arg = np.argmax(emotion_classifier.predict(gray_face))
     mood_label_arg = np.argmax(mood_classifier.predict(moody_face))
     emotion_text = emotion_labels[emotion_label_arg]
-    mood_text = emotion_labels[mood_label_arg]      # must use the same emotion_labels for specific purposed proven by the journal
+    mood_text = mood_labels[mood_label_arg]
 
     if gender_text == gender_labels[0]:
         color = (0, 0, 255)
diff --git a/src/utils/datasets.py b/src/utils/datasets.py
index a3a3ab3..b3d875f 100644
--- a/src/utils/datasets.py
+++ b/src/utils/datasets.py
@@ -113,7 +113,7 @@ def get_labels(dataset_name):
     elif dataset_name == 'KDEF':
         return {0: 'AN', 1: 'DI', 2: 'AF', 3: 'HA', 4: 'SA', 5: 'SU', 6: 'NE'}
     elif dataset_name == 'onigiri':
-        return {0: 'A021', 1: 'JSI', 2: 'SOMD', 11: 'KOBS', 131: 'SSOP'}
+        return {0: 'A021', 1: 'JSI', 2: 'SOMD', 3: 'KOBS', 4: 'SSOP'}
     else:
         raise Exception('Invalid dataset name')
 

From e66d90b047834425b5a2088f6237ef2f1f9f7c0c Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Fri, 5 Sep 2025 09:58:03 +0900
Subject: [PATCH 19/26] readme bro

---
 README.md | 41 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)

diff --git a/README.md b/README.md
index b9b33eb..4ae7f82 100644
--- a/README.md
+++ b/README.md
@@ -1 +1,42 @@
 # Multi-Modal-Image-Sentiment-Analysis
+
+## Overview
+This PR introduces a new **multidimensional 3D CNN model** within the Onigiri project.  
+The model leverages a large-scale dataset (~18TB) capturing regressional relationships between **mood, emotion, and facial expressions**, along with **gender attributes**.  
+
+The goal is to extend the multimodal project by enabling **mood determination** from image and face data, integrated with contextual metadata.
+
+---
+
+## Key Features
+- **New Data Integration**
+  - Added ~18TB of mass data on mood, emotion, and facial expression alongside gender.
+  - Preprocessing pipeline supports sequence-based image and embedding fusion.
+
+- **3D CNN Model Implementation**
+  - Input: `data_input` (sequence of facial image tensors).
+  - Auxiliary Input: `site_id_input` for contextual weather embedding.
+  - Weather embedding reshaped into a **weather map** and concatenated as an additional channel.
+  - Temporal-spatial Conv3D layers with ELU activations.
+  - Dense fully connected layers leading to mood prediction outputs.
+
+- **Output**
+  - Predicts **mood state** given image and contextual inputs.
+  - Designed to integrate seamlessly with existing multimodal architecture.
+
+---
+
+## Motivation
+This implementation expands Onigiri’s capability:
+- Moves beyond **basic sentiment analysis** to deeper **mood-level understanding**.
+- Bridges the gap between **visual emotion recognition** and **context-aware multimodal inference**.
+- Scales to massive datasets, aligning with the multimodal project’s growth roadmap.
+
+---
+
+## Next Steps
+- Train and benchmark the new model on curated dataset splits.
+- Compare performance against existing CNN and multimodal baselines.
+- Integrate evaluation metrics for mood detection accuracy and generalization.
+
+---

From 036036212e8d9c3b296cf0f0cc6d95d845622833 Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Fri, 5 Sep 2025 09:59:11 +0900
Subject: [PATCH 20/26] fixed error

---
 src/train_gender_classifier.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/src/train_gender_classifier.py b/src/train_gender_classifier.py
index 1a4bbf6..5e7ceae 100644
--- a/src/train_gender_classifier.py
+++ b/src/train_gender_classifier.py
@@ -50,7 +50,6 @@
     in_channels=all_possible_combinations_input.shape[4],
     out_features=y_true.shape[1] if y_true.ndim > 1 else 1,
     number_of_conv3d_layers=3,
-    num_weather_types=10,
     conv3d_channels=32,
     fc_features=128,
     spatial_kernel_size=3,

From 39e3c4861b6d9c68903147ca1d250815f7cc8fc8 Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Fri, 5 Sep 2025 10:00:36 +0900
Subject: [PATCH 21/26] on using ML parameters

---
 src/train_gender_classifier.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/src/train_gender_classifier.py b/src/train_gender_classifier.py
index 5e7ceae..4542d3b 100644
--- a/src/train_gender_classifier.py
+++ b/src/train_gender_classifier.py
@@ -66,7 +66,6 @@
 
 # ---- 3) Callbacks (match the style from your example) ----
 # fill these in (same variable names you used before)
-patience = 10
 log_file_path = "mood_train_log.csv"
 trained_models_path = "checkpoints/cnn3d_gsp"  # no extension; we'll format epochs/metrics into the filename
 
@@ -92,7 +91,7 @@
     all_possible_combinations_input, y_true,
     epochs=num_epochs,
     batch_size=batch_size,
-    validation_split=0.2,
+    validation_split=validation_split,
     callbacks=callbacks,
     verbose=1
 )

From 359f3d08ca5a5d6824fa15ce4e97c0292da02651 Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Fri, 5 Sep 2025 10:01:55 +0900
Subject: [PATCH 22/26] about leadtim 9000

---
 src/utils/separate_date_articulator_that_is_new.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/utils/separate_date_articulator_that_is_new.py b/src/utils/separate_date_articulator_that_is_new.py
index 9190efc..17aa47d 100644
--- a/src/utils/separate_date_articulator_that_is_new.py
+++ b/src/utils/separate_date_articulator_that_is_new.py
@@ -21,7 +21,7 @@ def accumulated_value_update(var_name, df):
     return df
 
 def selected_time_slice(df_weatherMood):
-    chosen_t0 = df_weatherMood["chosen_t0"][9000]
+    chosen_t0 = df_weatherMood[df_weatherMood["leadtime"]==9000]["t0"]
     (
         basetime_t0_hr_int,
         issued_time_hr_int,

From c4242534f22bf5c4bea924f014236006bf938aa5 Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Fri, 5 Sep 2025 10:32:02 +0900
Subject: [PATCH 23/26] index erroring

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---
 src/image_emotion_gender_demo.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/image_emotion_gender_demo.py b/src/image_emotion_gender_demo.py
index 3d28a85..6c42d2f 100644
--- a/src/image_emotion_gender_demo.py
+++ b/src/image_emotion_gender_demo.py
@@ -40,7 +40,7 @@
 # getting input model shapes for inference
 emotion_target_size = emotion_classifier.input_shape[1:3]
 gender_target_size = gender_classifier.input_shape[1:3]
-mood_target_size = mood_classifier.input_shape[0][1:3]
+mood_target_size = mood_classifier.input_shape[1:3]
 
 # loading images
 rgb_image = load_image(image_path, grayscale=False)

From a64247d81adb69dffb7376955b90497a283af900 Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Fri, 5 Sep 2025 10:32:34 +0900
Subject: [PATCH 24/26] csv file

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---
 src/train_gender_classifier.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/train_gender_classifier.py b/src/train_gender_classifier.py
index 4542d3b..7f7eb59 100644
--- a/src/train_gender_classifier.py
+++ b/src/train_gender_classifier.py
@@ -38,7 +38,7 @@
                                  do_random_crop=do_random_crop)
 
 # onigiri - as of 2025
-df_weather_mood = pd.read_csv('../datasets/onigiri.csv')
+df_weather_mood = pd.read_csv('../datasets/onigiri/sfj_weir_392834.csv')
 all_possible_combinations_input, y_true = return_emotions_mood_weather_mixer_combinations(df_weather_mood, batch_size,num_epochs,patience)
 all_possible_combinations_input = np.array(all_possible_combinations_input)
 y_true = np.array(list(y_true.values())) if isinstance(y_true, dict) else np.array(y_true)

From 055fec98f138d6f83751e92b7162c038fd92f9ce Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Fri, 5 Sep 2025 10:34:05 +0900
Subject: [PATCH 25/26] int to str

---
 src/utils/separate_date_articulator_that_is_new.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/src/utils/separate_date_articulator_that_is_new.py b/src/utils/separate_date_articulator_that_is_new.py
index 17aa47d..6e5ac68 100644
--- a/src/utils/separate_date_articulator_that_is_new.py
+++ b/src/utils/separate_date_articulator_that_is_new.py
@@ -65,12 +65,14 @@ def return_emotions_mood_weather_mixer_combinations(df_weatherMood, batch_size,n
         for weather in weather_types
     ]
 
-    all_timesteps = generate_monthly_timestamps(str(start), str(end))
+    all_timesteps = generate_monthly_timestamps(start, end)
 
     return combined, all_timesteps
 
 def generate_monthly_timestamps(start_timestamp, end_timestamp):
     # datetime 으로 변환
+    start_timestamp = str(start_timestamp)
+    end_timestamp = str(end_timestamp)
     start_date = datetime.strptime(start_timestamp, "%Y%m%d%H")
     end_date = datetime.strptime(end_timestamp, "%Y%m%d%H")
 

From b65891c7ec0069617dd8e2da522262e7b623c92b Mon Sep 17 00:00:00 2001
From: kwon-encored <thkwon@encoredtech.com>
Date: Fri, 5 Sep 2025 10:47:01 +0900
Subject: [PATCH 26/26] instruction for GitHub CoPilot

---
 .github/copilot-instructions.md | 59 +++------------------------------
 1 file changed, 4 insertions(+), 55 deletions(-)

diff --git a/.github/copilot-instructions.md b/.github/copilot-instructions.md
index d2cece9..c5b662f 100644
--- a/.github/copilot-instructions.md
+++ b/.github/copilot-instructions.md
@@ -1,58 +1,7 @@
 description: 'Python coding conventions and guidelines'
 applyTo: '**/*.py'
 ---
-
-# Python Coding Conventions
-
-## Python Instructions
-
-- Write clear and concise comments for each function.
-- Ensure functions have descriptive names and include type hints.
-- Provide docstrings following PEP 257 conventions.
-- Use the `typing` module for type annotations (e.g., `List[str]`, `Dict[str, int]`).
-- Break down complex functions into smaller, more manageable functions.
-- Write docstrings and comments primarily in Korean (unless external libraries or public APIs require English).
-
-## General Instructions
-
-- Always prioritize readability and clarity.
-- For algorithm-related code, include explanations of the approach used.
-- Write code with good maintainability practices, including comments on why certain design decisions were made.
-- Handle edge cases and write clear exception handling.
-- For libraries or external dependencies, mention their usage and purpose in comments.
-- Use consistent naming conventions and follow language-specific best practices.
-- Ensure all referenced functions, classes, and variables are properly declared before use.
-- Carefully read and comprehensively understand each function, loop, and conditional (and their combinations); when appropriate, refactor into more efficient one-liners/two-liners or leverage built-in/vectorized methods from `numpy`, `pandas`, `datetime`, `itertools`, etc., while preserving behavior and clarity.
-- Write concise, efficient, and idiomatic code that is also easily understandable.
-
-## Code Style and Formatting
-- Use snake_case for variable and function names. Use CamelCase for class names. Follow PEP 8 style guidelines. Include type hints for function parameters and return types.
-- Follow the **PEP 8** style guide for Python.
-- Maintain proper indentation (use 4 spaces for each level of indentation).
-- Ensure lines do not exceed 79 characters.
-- Place function and class docstrings immediately after the `def` or `class` keyword.
-- Use blank lines to separate functions, classes, and code blocks where appropriate.
-
-## Edge Cases and Testing
-
-- Always include test cases for critical paths of the application.
-- Account for common edge cases like empty inputs, invalid data types, and large datasets.
-- Include comments for edge cases and the expected behavior in those cases.
-- Write unit tests for functions and document them with docstrings explaining the test cases.
-
-## Example of Proper Documentation
-
-```python
-def calculate_area(radius: float) -> float:
-    """
-    원의 면적을 계산하는 함수
-    
-    주어진 반지름(`radius`)을 이용하여 원의 면적을 계산한다. 
-    면적은 π * (반지름^2) 공식을 사용한다.
-    
-    :param float radius: 원의 반지름
-    :return: 원의 면적 값
-    :rtype: float
-    """
-    import math
-    return math.pi * radius ** 2
+- When performing a code review, ensure that variable and function names use snake_case, and class names use CamelCase, following PEP 8 style guidelines.
+- When reviewing functions, check if loops or conditionals can be simplified with built-in or vectorized methods (e.g., numpy, pandas, datetime, itertools) while preserving clarity and behavior.
+- When reviewing a function, check that its name is appropriate and corresponds to and clearly describes its purpose.
+- When reviewing a function, check that its name clearly describes its purpose and that variable names are appropriate and descriptive.