pages/Dashboard.py

import streamlit as st
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from Utility.data_loader  import load_train_series,load_train_events,load_sample_submission,load_test_series
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder, StandardScaler
from xgboost import XGBClassifier  # or XGBRegressor depending on your task
import xgboost as xgb
import numpy as np

@st.cache_data
def load_sampled_data():
    # df3 = pd.read_parquet("train_series.parquet", columns=['series_id', 'step', 'anglez', 'enmo'])
    # df4 = pd.read_parquet("test_series.parquet", columns=['series_id', 'step', 'anglez', 'enmo'])
    df2 = pd.read_csv("train_events.csv")

    # Sample safely based on available data
    # df3_sample = df3.sample(n=min(5_000_000, len(df3)), random_state=42)
    # df4_sample = df4.sample(n=min(1_000_000, len(df4)), random_state=42)

    return df2

# Load
# df3, df4, df2 = load_sampled_data()
df2 = load_sampled_data()
# df = pd.concat([df3, df4], axis=0, ignore_index=True)
# merged_df = pd.merge(df, df2, on=['series_id', 'step'], how='inner')

merged_df = pd.read_csv("merged_df.csv")

# Rename timestamp columns if they exist
if 'timestamp_x' in merged_df.columns:
    merged_df.rename(columns={'timestamp_x': 'sensor_timestamp'}, inplace=True)
if 'timestamp_y' in merged_df.columns:
    merged_df.rename(columns={'timestamp_y': 'event_timestamp'}, inplace=True)

st.title("📊 Step Distribution Analysis")

# Layout: 2 columns
col1, col2 = st.columns([1, 1])  # Equal width
# ----- Column 1: Boxplot -----
with col1:
    st.subheader("📦 Boxplot of Step")
    fig, ax = plt.subplots(figsize=(6, 4))  # Adjusted for better visibility
    sns.boxplot(x=df2['step'], ax=ax, color='steelblue')
    ax.set_title("Distribution of Step Count", fontsize=14)
    ax.set_xlabel("Step", fontsize=12)
    st.pyplot (fig)

# ----- Column 2: Insights -----
with col2:
    st.subheader("🧠 Insights from the Boxplot")
    st.markdown("""
        <small>
        <b>Central Tendency:</b><br>
        - The <b>median</b> is close to the center of the box, suggesting a fairly symmetric distribution within the interquartile range (IQR).<br>
        <b>Spread:</b><br>
        - A <b>wide IQR</b> indicates significant variability in the step counts across sessions.<br>
        <b>Outliers:</b><br>
        - The <b>dots on the right</b> are outliers — representing very high step counts.<br>
        - These could reflect either:<br>
        - <b>Legitimate long-duration recordings</b><br>
        - Or <b>data quality issues</b> (e.g., duplication or sensor errors)
        <b>Distribution Shape:</b><br>
        - A <b>longer left whisker</b> implies a <b>left-skewed</b> distribution.<br>
        - Most sessions have <b>lower step values</b>, with a few very high outliers.
        </small>
        """, unsafe_allow_html=True)


#st.write("1. Data Visualization - Scatter Plot (feature vs feature or vs target)")
# Assume merged_df is already defined or loaded
df_sample = merged_df  # or use df_sample = merged_df.sample(n=50000) to downsample

st.subheader("Scatter Plot: anglez vs enmo")

col1, col2 = st.columns([1, 1])

with col1:
    #st.subheader("Scatter Plot: anglez vs enmo")
    # fig, ax = plt.subplots(figsize=(6, 4))
    # sns.scatterplot(x=df['anglez'], y=df['enmo'], ax=ax)
    # ax.set_title("Scatter Plot: anglez vs enmo")
    # st.pyplot(fig)

    # Create the plot
    fig, ax = plt.subplots(figsize=(6, 4))
    sns.scatterplot(x='anglez', y='enmo', data=df_sample, ax=ax)
    ax.set_title("Scatter Plot: anglez vs enmo")

    # Display in Streamlit
    st.pyplot(fig)

with col2:
    st.markdown("""
    <small>
    <b>1. Clustered Points:</b> Most `enmo` values are near 0, suggesting low movement.<br>
    <b>2. Symmetry:</b> Spread is balanced on both sides of anglez (±), indicating no directional bias.<br>
    <b>3. Weak Correlation:</b> No visible trend, suggesting independence between `anglez` and `enmo`.<br>
    <b>4. Outliers:</b> A few high `enmo` points may indicate sudden or intense movement.<br>
    <b>5. Interpretation:</b> Most data reflects light activity or rest, regardless of body orientation.
    </small>
    """, unsafe_allow_html=True)


# df_sample = merged_df.sample(n=10000)  # adjust sample size for performance

# # Subheader
# st.subheader("Pair Plot of Features")

# # Create pairplot
# fig = sns.pairplot(df_sample[['anglez', 'enmo', 'step']])
# fig.fig.suptitle("Pair Plot of Features", y=1.02)

# # Display in Streamlit
# st.pyplot(fig)
# Define columns to plot

col1, col2 = st.columns([1, 1])  # Equal width

# Column 1: Pair Plot
with col1:
    st.subheader("📈 Pair Plot of Features")
    fig = sns.pairplot(merged_df[['anglez', 'enmo', 'step']])
    st.pyplot(fig)

# Column 2: Insights
with col2:
    st.subheader("🧠 Insights from Pair Plot")
    st.markdown("""
<div style='font-size: 14px'>

### 📊 Distribution Insights:
- **anglez**: Symmetric distribution peaking near -50 to 0.
- **enmo**: Right-skewed, most values below 0.1.
- **step**: Right-skewed, with a few large outliers.

### 🔁 Pairwise Relationships:
- **anglez vs enmo**: No clear trend; cone-like shape.
- **anglez vs step**: No correlation; looks uniformly scattered.
- **enmo vs step**: Clustered at low values. High steps sometimes with low enmo.

### 💡 Summary:
- Features appear largely **uncorrelated**.
- Helps identify **data distributions** and potential **outliers**.
- Can assist in **feature selection/engineering**.

</div>
""", unsafe_allow_html=True)

# plot_columns = ['anglez', 'enmo', 'step']

# # Safety check: make sure required columns exist
# if all(col in merged_df.columns for col in plot_columns):

#     # Check data size and sample accordingly
#     max_rows = len(merged_df)
#     sample_size = min(10000, max_rows)  # Don't exceed available rows

#     df_sample = merged_df.sample(n=sample_size)

#     # Subheader
#     st.subheader("Pair Plot of Features")

#     # Create pairplot
#     fig = sns.pairplot(df_sample[plot_columns])
#     fig.fig.suptitle("Pair Plot of Features", y=1.02)

#     # Display in Streamlit
#     st.pyplot(fig)

# else:
#     st.error("One or more required columns ('anglez', 'enmo', 'step') are missing in the dataset.")


# Plot
fig, axes = plt.subplots(1, 2, figsize=(14, 5))

sns.histplot(df_sample['anglez'], kde=True, bins=50, ax=axes[0])
axes[0].set_title("Distribution of anglez")

sns.histplot(df_sample['enmo'], kde=True, bins=50, ax=axes[1])
axes[1].set_title("Distribution of enmo")

plt.tight_layout()
st.pyplot(fig)

# Show insights side by side
col1, col2 = st.columns(2)

with col1:
    st.markdown("""
    <div style='font-size: 14px'>
    <h3> 📈 Distribution of `anglez`: </h3>
    - The distribution is **roughly symmetric**, centered around **-50 to 0**.
    - It resembles a **left-heavy bell shape**, suggesting:
      - Most sensor angles were **tilted negatively**.
      - Indicates a **natural resting position** or specific posture.
    </div>
    """, unsafe_allow_html=True)

with col2:
    st.markdown("""
    <div style='font-size: 14px'>
    <h3> 📉 Distribution of `enmo`: </h3>
    - Highly **right-skewed** (sharp peak near zero).
    - The majority of `enmo` values are **very small** (< 0.05), indicating:
      - **Minimal movement or low activity** in most sessions.
      - Few data points reflect **moderate to high movement**.
    </div>
    """, unsafe_allow_html=True)



# st.write("Multicollinearity Check - Correlation Matrix")
# features = ['anglez', 'enmo', 'step', 'night']
# df_subset = merged_df[features]

# # Streamlit title
# st.subheader("Multicollinearity Check - Correlation Matrix")

# # Calculate correlation matrix
# corr_matrix = df_subset.corr()

# # Plot heatmap
# fig, ax = plt.subplots(figsize=(6, 4))
# sns.heatmap(corr_matrix, annot=True, cmap='coolwarm', ax=ax)
# ax.set_title("Correlation Matrix")

# # Display in Streamlit
# st.pyplot(fig)


st.subheader("Multicollinearity Check - Correlation Matrix")

# Select relevant features
features = ['anglez', 'enmo', 'step', 'night']
df_subset = merged_df[features]

# Calculate correlation matrix
corr_matrix = df_subset.corr()

# Create plot
fig, ax = plt.subplots(figsize=(6, 4))
sns.heatmap(corr_matrix, annot=True, cmap='coolwarm', center=0, fmt=".3f", ax=ax)
ax.set_title("Correlation Matrix")

# Layout in two columns
col1, col2 = st.columns(2)

# Column 1: Heatmap
with col1:
    st.pyplot(fig)

# Column 2: Textual Insights
with col2:
    st.markdown("""
    ### 🔍 Insights from Correlation Matrix 

    - **`anglez` & `enmo`**:  
      🔸 Weak negative correlation (**-0.11**) — suggests minimal linear relationship.

    - **`step` & `night`**:  
      ⚠️ Perfect correlation (**1.00**) — indicates **redundancy**, likely representing the same event in different forms.

    - **Overall**:  
      ✅ Low multicollinearity across most features — safe for modeling.  
      📝 Recommend removing either `step` or `night` to reduce feature duplication.
    """)


# Encode
le = LabelEncoder()
merged_df['series_id'] = le.fit_transform(merged_df['series_id'])
merged_df['event'] = le.fit_transform(merged_df['event'])

# Drop columns with string or datetime values
drop_cols = ['sensor_timestamp', 'event_timestamp', 'night', 'step', 'sleep_duration_hrs', 'series_id']
df_cleaned = merged_df.drop(columns=[col for col in drop_cols if col in merged_df.columns])

# Ensure only numeric features in X
X = df_cleaned.drop('event', axis=1).select_dtypes(include=[np.number])
y = merged_df['event']

# Split and scale
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=27)

st.subheader("Feature Importance")
# Create model instance
xgb_model = XGBClassifier(use_label_encoder=False, eval_metric='logloss')  # example for classification

# Fit the model
xgb_model.fit(X_train, y_train)

# Plot feature importance
fig, ax = plt.subplots(figsize=(6, 4))
xgb.plot_importance(xgb_model, ax=ax)
ax.set_title("XGBoost Feature Importance")

# Show in Streamlit
st.subheader("XGBoost Feature Importance")



col1, col2 = st.columns(2)

# Column 1: Plot
with col1:
    st.pyplot(fig)
    st.markdown("""
#### 🚫 Low-Impact Features:
- Features like `step` and `night` (excluded in this plot) showed **minimal or redundant contribution**.
- 🔁 You may consider **removing** them to simplify the model.
""")
# Column 2: Insights
with col2:
 st.markdown("""
<small>
<h3> 🔍 XGBoost Feature Importance: Key Insights </h3>

#### 📌 Top Features:
- 🔹 **`anglez`** — Highest importance score (**1557**)
- 🔹 **`enmo`** — Close second with score (**1546**)

#### ✅ Summary:
- Both `anglez` and `enmo` contribute **significantly** to the model.
- Their high scores reflect **strong influence** in predicting the target variable.

#### 💡 Interpretation:
- These features likely capture **activity level** or **sleep posture** patterns.
- Keeping both is **recommended** for accurate classification.
</small>

""", unsafe_allow_html=True)