Dashboard Features

.streamlit/config.toml

@@ -0,0 +1,5 @@
+[theme]
+primaryColor = '#1c83e1'
+backgroundColor = '#ffffff'
+secondaryBackgroundColor = '#f0f2f6'
+textColor = '#000000'

app/app.py

@@ -0,0 +1,79 @@
+import streamlit as st
+from data_processing import load_data, clean_and_prepare_data
+from utils import data_quality_check
+from plots import plot_time_series, plot_area, create_scatter_plot, create_correlation_analysis
+import pandas as pd
+
+# Load datasets
+datasets = load_data()
+
+# Streamlit UI
+st.title("Solar Radiation Data Analysis")
+
+# Sidebar for dataset selection
+dataset_name = st.sidebar.selectbox("Select Dataset", ("Benin", "Togo", "Sierra Leone"))
+df = datasets[dataset_name]
+
+# Display the dataset summary
+st.write(f"### {dataset_name} Dataset Summary")
+st.write(df.describe())
+
+# Sidebar: Want to Clean Section
+clean_data = st.sidebar.checkbox("Want to Clean Data")
+
+if clean_data:
+    # Data Quality Check Before Cleaning
+    quality_results_before = data_quality_check(df)
+    st.write("#### Data Quality Check Results (Before Cleaning)")
+    st.write(pd.DataFrame(quality_results_before).T)
+
+    # Clean Data
+    df_cleaned = clean_and_prepare_data(df)
+
+    # Data Quality Check After Cleaning
+    quality_results_after = data_quality_check(df_cleaned)
+    st.write("#### Data Quality Check Results (After Cleaning)")
+    st.write(pd.DataFrame(quality_results_after).T)
+
+    # Display cleaned data
+    st.write(f"### {dataset_name} Cleaned Data")
+    st.write(df_cleaned.head())
+
+# Sidebar: Analysis Selection
+st.sidebar.write("### Which to Analyze?")
+analyze_uncleaned = st.sidebar.checkbox("Analyze Uncleaned Data")
+analyze_cleaned = st.sidebar.checkbox("Analyze Cleaned Data")
+
+# Determine which dataset to analyze
+df_to_analyze = None
+data_label = ""
+
+if analyze_uncleaned:
+    df_to_analyze = df
+    data_label = "Uncleaned Data"
+elif analyze_cleaned and clean_data:
+    df_to_analyze = df_cleaned
+    data_label = "Cleaned Data"
+
+# Display analysis options if either checkbox is selected
+if analyze_uncleaned or (analyze_cleaned and clean_data):
+    st.sidebar.write(f"### Analysis Options for {data_label}")
+    plot_area_selected = st.sidebar.checkbox("Area Plot")
+    plot_time_series_selected = st.sidebar.checkbox("Time Series Plot")
+    plot_scatter_selected = st.sidebar.checkbox("Scatter Plot")
+    plot_correlation_selected = st.sidebar.checkbox("Correlation Analysis")
+
+    # Perform selected analyses
+    if plot_correlation_selected and df_to_analyze is not None:
+        create_correlation_analysis(df_to_analyze, dataset_name)
+
+    if plot_area_selected and df_to_analyze is not None:
+        plot_area(df_to_analyze, dataset_name)
+
+    if plot_scatter_selected and df_to_analyze is not None:
+        create_scatter_plot(df_to_analyze)
+
+    if plot_time_series_selected and df_to_analyze is not None:
+        plot_time_series(df_to_analyze, dataset_name)
+else:
+    st.warning("Please select either 'Analyze Uncleaned Data' or 'Analyze Cleaned Data'.")

app/data_processing.py

@@ -0,0 +1,24 @@
+import pandas as pd
+import numpy as np
+
+COLUMNS_TO_CHECK = ['GHI', 'DNI', 'DHI', 'ModA', 'ModB', 'WS', 'WSgust']
+
+def load_data():
+    datasets = {
+        "Benin": pd.read_csv('../data/benin-malanville.csv'),
+        "Togo": pd.read_csv('../data/togo-dapaong_qc.csv'),
+        "Sierra Leone": pd.read_csv('../data/sierraleone-bumbuna.csv')
+    }
+    return datasets
+
+def clean_data(df):
+    df = df[(df[COLUMNS_TO_CHECK] >= 0).all(axis=1)]
+    z_scores = np.abs((df[COLUMNS_TO_CHECK] - df[COLUMNS_TO_CHECK].mean()) / df[COLUMNS_TO_CHECK].std())
+    df = df[(z_scores < 3).all(axis=1)]
+    return df
+
+def clean_and_prepare_data(df):
+    df_cleaned = clean_data(df)
+    df_cleaned['Timestamp'] = pd.to_datetime(df_cleaned['Timestamp'])
+    df_cleaned.set_index('Timestamp', inplace=True)
+    return df_cleaned

app/main.py

@@ -16,11 +16,12 @@
 st.title("Solar Radiation Data Analysis")
 
 # Load data
-df = da.load_data('data/benin-malanville.csv')
+df = da.load_data('../data/benin-malanville.csv')
+
 
 # Sidebar
 option = st.sidebar.selectbox("Select Analysis", ("Summary Statistics", "Time Series Analysis", 
-                                                  "Correlation Analysis", "Wind Analysis", 
+                                                  "Correlation Analysis", "Create Wind Plot", 
                                                   "Temperature Analysis", "Histograms", 
                                                   "Z-Score Analysis", "Bubble Chart"))
 
@@ -31,8 +32,8 @@
     da.time_series_analysis(df)
 elif option == "Correlation Analysis":
     da.correlation_analysis(df)
-elif option == "Wind Analysis":
-    da.wind_analysis(df)
+elif option == "Create Wind Analysis":
+    da.create_polar_plot(df, 'Wind Direction')
 elif option == "Temperature Analysis":
     da.temperature_analysis(df)
 elif option == "Histograms":

app/plots.py

@@ -0,0 +1,42 @@
+import matplotlib.pyplot as plt
+import seaborn as sns
+import streamlit as st
+
+def plot_time_series(df, dataset_name):
+    fig, ax = plt.subplots(figsize=(14, 8))
+    df[['GHI', 'DNI', 'DHI', 'Tamb']].plot(ax=ax)
+    plt.title(f'Time Series Analysis of GHI, DNI, DHI, and Tamb in {dataset_name}')
+    st.pyplot(fig)
+
+import matplotlib.pyplot as plt
+import streamlit as st
+
+def plot_area(df, title, columns):
+    try:
+        # Check if any column contains both positive and negative values
+        for col in columns:
+            if df[col].min() < 0 and df[col].max() > 0:
+                raise ValueError(f"Column '{col}' contains both positive and negative values, which is not allowed in an area plot.")
+
+        # Create area plot
+        fig, ax = plt.subplots()
+        df[columns].plot(kind='area', ax=ax, alpha=0.5)
+        ax.set_title(title)
+        plt.xticks(rotation=45)
+        plt.tight_layout()
+        st.pyplot(fig)
+
+    except ValueError as e:
+        # Handle the ValueError and provide an appropriate message
+        st.error(f"Error in plotting area chart: {e}")
+
+def create_scatter_plot(df):
+    fig, ax = plt.subplots()
+    sns.scatterplot(data=df, x='RH', y='Tamb', ax=ax)
+    plt.title("Scatter Plot: Temperature (Tamb) vs Relative Humidity (RH)")
+    st.pyplot(fig)
+
+def create_correlation_analysis(df, dataset_name):
+    correlation = df[['RH', 'Tamb', 'TModA', 'TModB']].corr()
+    st.write(f"### Correlation Analysis - {dataset_name}")
+    st.write(correlation)

app/utils.py

@@ -0,0 +1,12 @@
+import pandas as pd
+import numpy as np
+
+def data_quality_check(df):
+    COLUMNS_TO_CHECK = ['GHI', 'DNI', 'DHI', 'ModA', 'ModB', 'WS', 'WSgust']
+    data_quality = {
+        "Column": COLUMNS_TO_CHECK,
+        "Missing Values": df[COLUMNS_TO_CHECK].isnull().sum().values,
+        "Outliers": (np.abs((df[COLUMNS_TO_CHECK] - df[COLUMNS_TO_CHECK].mean()) / df[COLUMNS_TO_CHECK].std()) > 3).sum().values,
+        "Incorrect Entries": (df[COLUMNS_TO_CHECK] < 0).sum().values
+    }
+    return pd.DataFrame(data_quality)