Upload 8 files

app (1).py

@@ -0,0 +1,188 @@
+import streamlit as st
+import pickle
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+# ----------- Page Configuration ------------
+st.set_page_config("Sleep State Detection", layout="wide")
+st.title(" Sleep State Detection App")
+
+# ----------- Navigation Sidebar ------------
+page = st.sidebar.radio("📍 Navigation", ["Overview", "EDA", "Predict"])
+
+# ----------- Load Data & Model ------------
+@st.cache_data
+def load_data(filepath):
+    return pd.read_csv(filepath)
+
+@st.cache_data
+def load_model(filepath):
+    with open(filepath, "rb") as f:
+        return pickle.load(f)
+
+# ----------- Histogram Plot Function ------------
+def plot_histogram(df, column, color):
+    fig, ax = plt.subplots()
+    sns.histplot(df[column], bins=30, kde=True, color=color, ax=ax)
+    ax.set_title(f"Distribution of {column}")
+    st.pyplot(fig, use_container_width=True)
+    plt.close()
+
+# ----------- Overview Page ------------
+if page == "Overview":
+    st.header(" Project Overview")
+    st.markdown("This app detects **sleep onset** and **wake-up states** using `anglez` and `enmo` values from a wearable sensor.")
+
+    with st.expander(" Problem Statement"):
+        st.markdown("""
+        - Detect sleep and wake-up periods using wearable sensor data.  
+        - Sleep is estimated from low-movement patterns.
+        """)
+
+    with st.expander(" Objective"):
+        st.markdown("""
+        - Classify sleep vs wake states  
+        - Build an ML model that generalizes to real users  
+        """)
+
+    with st.expander(" Constraints"):
+        st.markdown("""
+        - Missing or noisy data  
+        - Ensure low false alarms  
+        - Simple, real-time capable models  
+        """)
+
+# ----------- EDA Page ------------
+elif page == "EDA":
+    st.header(" Exploratory Data Analysis")
+    df = load_data("cleaned_sleep_data.csv")
+
+    # ---- Multi-select Filter Sleep/Wake ----
+    st.markdown("### 🔎 Filter by Sleep State")
+    state_options = st.multiselect("Select sleep states to display", ["Sleep", "Wake-Up"], default=["Sleep", "Wake-Up"])
+
+    if state_options:
+        filter_map = {"Sleep": 1, "Wake-Up": 0}
+        selected_values = [filter_map[opt] for opt in state_options]
+        df = df[df["sleep"].isin(selected_values)]
+
+    # ---- Histograms ----
+    col1, col2 = st.columns(2)
+    with col1:
+        st.subheader(" Anglez")
+        plot_histogram(df, "anglez", "#74b9ff")
+        st.markdown("- Distribution typical of rest posture")
+
+    with col2:
+        st.subheader(" ENMO")
+        plot_histogram(df, "enmo", "#81ecec")
+        st.markdown("- ENMO reflects movement intensity")
+
+    # ---- Pairplot ----
+    st.subheader(" Feature Relationships")
+    with st.spinner("Creating pairplot..."):
+        pairplot_fig = sns.pairplot(df, vars=['anglez', 'enmo'], hue='sleep', palette='coolwarm')
+        st.pyplot(pairplot_fig.fig, use_container_width=True)
+        plt.close()
+
+    # ---- Boxplots ----
+    st.subheader(" Boxplots")
+    fig, axs = plt.subplots(1, 2, figsize=(12, 5))
+    sns.boxplot(y=df["anglez"], ax=axs[0], color='#74b9ff')
+    axs[0].set_title("Boxplot: Anglez")
+    sns.boxplot(y=df["enmo"], ax=axs[1], color='#81ecec')
+    axs[1].set_title("Boxplot: ENMO")
+    st.pyplot(fig, use_container_width=True)
+    plt.close()
+
+    # ---- Correlation ----
+    st.subheader(" Correlation Heatmap")
+    fig, ax = plt.subplots()
+    sns.heatmap(df[["anglez", "enmo"]].corr(), annot=True, cmap="coolwarm", ax=ax)
+    st.pyplot(fig, use_container_width=True)
+    plt.close()
+
+# ----------- Predict Page ------------
+elif page == "Predict":
+    st.header(" Sleep Prediction")
+    model = load_model("new_sleep_model.pkl")
+
+    # ---- Sleep/Wake Filter Dropdown
+    st.markdown("###  Select Sample Type")
+    state_choice = st.selectbox("Choose Sample Type", ["Custom Input", "Sleep Sample", "Wake-Up Sample"])
+
+    # ---- Default Values Based on Choice
+    if state_choice == "Sleep Sample":
+        default_anglez = -45.0
+        default_enmo = 0.01
+    elif state_choice == "Wake-Up Sample":
+        default_anglez = 20.0
+        default_enmo = 0.2
+    else:
+        default_anglez = 0.0
+        default_enmo = 0.0
+
+    # ---- Input Sliders
+    col1, col2 = st.columns(2)
+    with col1:
+        anglez = st.slider(" Anglez (-180° to 180°)", -180.0, 180.0, default_anglez)
+    with col2:
+        enmo = st.slider(" ENMO (0.0 to 1.0)", 0.0, 1.0, default_enmo)
+
+    # ---- Prediction
+    if st.button(" Predict Sleep State"):
+        input_vector = np.array([[anglez, enmo]])
+        prediction = model.predict(input_vector)[0]
+
+        if hasattr(model, "predict_proba"):
+            proba = model.predict_proba(input_vector)[0]
+            confidence = round(np.max(proba) * 100, 2)
+            st.metric(" Model Confidence", f"{confidence}%")
+
+        labels = {
+            0: (" Wake-Up", "You're likely **awake** — motion and posture detected."),
+            1: (" Sleep Onset", "Low motion detected — you may be **falling asleep**.")
+        }
+
+        label, message = labels.get(prediction, ("❓ Unknown", "⚠️ No clear state detected."))
+        st.success(f"** Predicted State:** {label}")
+        st.info(message)
+
+        # Display image based on prediction
+        if prediction == 1:
+            st.image(
+                "https://huggingface.co/spaces/Saidee156/AI_SLEEP_DETECTION/resolve/main/th%20(1).jpeg",
+                use_container_width=True,
+            )
+            st.markdown("""
+            ###  Personalized Sleep Tips
+             **Tips to Fall Asleep Faster**  
+            -  Avoid screens 30 mins before bed  
+            -  Keep the room cool and dark  
+            -  Try deep breathing or meditation  
+            -  Stick to a regular sleep schedule  
+            """)
+        else:
+            st.image(
+                "https://huggingface.co/spaces/Saidee156/AI_SLEEP_DETECTION/resolve/main/cute-little-boy-wake-up-in-morning-stretching-hands-on-bed-in-bedroom-vector.jpg",
+                use_container_width=True,
+            )
+            st.markdown("""
+            ###  Tips to Wake Up Refreshed
+            -  Get morning sunlight exposure  
+            -  Move or stretch your body  
+            -  Eat a light, energizing breakfast  
+            -  Cold water splash or shower helps  
+            """)
+
+
+
+
+
+
+
+
+
+

model.ipynb

@@ -0,0 +1,265 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "50ddcbd1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pickle"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "9a90403c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\deekshi\\AppData\\Local\\Temp\\ipykernel_31352\\4176903524.py:2: UserWarning: [16:57:16] WARNING: C:\\actions-runner\\_work\\xgboost\\xgboost\\src\\data\\../common/error_msg.h:82: If you are loading a serialized model (like pickle in Python, RDS in R) or\n",
+      "configuration generated by an older version of XGBoost, please export the model by calling\n",
+      "`Booster.save_model` from that version first, then load it back in current version. See:\n",
+      "\n",
+      "    https://xgboost.readthedocs.io/en/stable/tutorials/saving_model.html\n",
+      "\n",
+      "for more details about differences between saving model and serializing.\n",
+      "\n",
+      "  model = pickle.load(f)\n"
+     ]
+    }
+   ],
+   "source": [
+    "with open(\"xgboost_sleep_model.pkl\",'rb') as f:\n",
+    "    model = pickle.load(f)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "eaabe4bf",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: pandas in d:\\anaconda\\lib\\site-packages (2.2.2)\n",
+      "Requirement already satisfied: scikit-learn in d:\\anaconda\\lib\\site-packages (1.4.2)\n",
+      "Requirement already satisfied: xgboost in d:\\anaconda\\lib\\site-packages (3.0.0)\n",
+      "Requirement already satisfied: openpyxl in d:\\anaconda\\lib\\site-packages (3.1.2)\n",
+      "Requirement already satisfied: numpy>=1.26.0 in d:\\anaconda\\lib\\site-packages (from pandas) (1.26.4)\n",
+      "Requirement already satisfied: python-dateutil>=2.8.2 in d:\\anaconda\\lib\\site-packages (from pandas) (2.9.0.post0)\n",
+      "Requirement already satisfied: pytz>=2020.1 in d:\\anaconda\\lib\\site-packages (from pandas) (2024.1)\n",
+      "Requirement already satisfied: tzdata>=2022.7 in d:\\anaconda\\lib\\site-packages (from pandas) (2023.3)\n",
+      "Requirement already satisfied: scipy>=1.6.0 in d:\\anaconda\\lib\\site-packages (from scikit-learn) (1.13.1)\n",
+      "Requirement already satisfied: joblib>=1.2.0 in d:\\anaconda\\lib\\site-packages (from scikit-learn) (1.4.2)\n",
+      "Requirement already satisfied: threadpoolctl>=2.0.0 in d:\\anaconda\\lib\\site-packages (from scikit-learn) (2.2.0)\n",
+      "Requirement already satisfied: et-xmlfile in d:\\anaconda\\lib\\site-packages (from openpyxl) (1.1.0)\n",
+      "Requirement already satisfied: six>=1.5 in d:\\anaconda\\lib\\site-packages (from python-dateutil>=2.8.2->pandas) (1.16.0)\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "pip install pandas scikit-learn xgboost openpyxl\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "ca8672ba",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "✅ Accuracy: 0.5952008346374543\n",
+      "🎉 Model saved successfully as 'new_sleep_model.pkl'\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "import xgboost as xgb\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.metrics import accuracy_score\n",
+    "import pickle\n",
+    "\n",
+    "# ✅ Step 1: Load the cleaned CSV file\n",
+    "df = pd.read_csv(r\"D:\\Child_sleep_detect\\cleaned_sleep_data.csv\")\n",
+    "\n",
+    "# ✅ Step 2: Drop missing values\n",
+    "df.dropna(inplace=True)\n",
+    "\n",
+    "# ✅ Step 3: Define features and target\n",
+    "X = df[['anglez', 'enmo']]\n",
+    "\n",
+    "# ✅ Step 4: Manually encode 'sleep' column ('onset' = 0, 'wakeup' = 1)\n",
+    "y = df['sleep'].map({'onset': 0, 'wakeup': 1})\n",
+    "\n",
+    "# ✅ Step 5: Train-test split\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
+    "\n",
+    "# ✅ Step 6: Train XGBoost classifier\n",
+    "model = xgb.XGBClassifier()\n",
+    "model.fit(X_train, y_train)\n",
+    "\n",
+    "# ✅ Step 7: Evaluate the model\n",
+    "y_pred = model.predict(X_test)\n",
+    "acc = accuracy_score(y_test, y_pred)\n",
+    "print(\"✅ Accuracy:\", acc)\n",
+    "\n",
+    "# ✅ Step 8: Save the model\n",
+    "with open(\"new_sleep_model.pkl\", \"wb\") as f:\n",
+    "    pickle.dump(model, f)\n",
+    "\n",
+    "print(\"🎉 Model saved successfully as 'new_sleep_model.pkl'\")\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "7c079ac3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0       0\n",
+       "1       1\n",
+       "2       0\n",
+       "3       1\n",
+       "4       0\n",
+       "       ..\n",
+       "9580    1\n",
+       "9581    0\n",
+       "9582    1\n",
+       "9583    0\n",
+       "9584    1\n",
+       "Name: sleep, Length: 9585, dtype: int64"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "y"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "18a6341f",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "badf06a5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a4376d7c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1752fabb",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "77d9b049",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7104aff0",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "91b3c488",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "11a7572f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dfe336dd",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b680af21",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "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": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

new_sleep_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c5b88b36ce5376216cd51d57645dd901121345dde0ed426ec1744d10f54368c
+size 301334

requirements.txt

@@ -0,0 +1,7 @@
+streamlit
+pandas
+numpy
+scikit-learn
+xgboost
+matplotlib
+seaborn