making changes to file call defined functions and explicit calls to m…

app_modules/functions_app.py

@@ -1,6 +1,6 @@
 import pandas as pd
-from .helper_modules.geodata import add_state_abbreviations, merge_with_fips, merge_with_geolocation
-from .query_gbq import query_table
+from app_modules.helper_modules.geodata import add_state_abbreviations, merge_with_fips, merge_with_geolocation
+from app_modules.query_gbq import query_table
 from google.api_core.exceptions import GoogleAPIError
 
 

app_modules/visualizations_app.py

@@ -6,14 +6,61 @@
 import plotly.graph_objects as go
 from plotly.subplots import make_subplots
 import requests
-from .functions_app import (
+from app_modules.functions_app import (
     prep_bird_flu_data,
     prep_wild_bird_data,
     prep_egg_price_data,
     prep_stock_price_data,
 )
 
 
+# === New Function: CREATE GEOSPATIAL PLOT ===
+def create_geospatial(data):
+    """
+    Creates a geospatial plot using latitude, longitude, and flock size.
+    """
+    fig = px.scatter_mapbox(
+        data,
+        lat="lat",
+        lon="lng",
+        size="Flock Size",
+        color="Flock Size",
+        color_continuous_scale="Viridis",
+        mapbox_style="carto-positron",
+        zoom=3,
+        title="Geospatial Visualization"
+    )
+    return fig
+
+
+# === New Function: CREATE TIME SERIES PLOT ===
+def create_time_series(egg_price_df, stock_price_df):
+    """
+    Creates a time series plot comparing egg prices and stock prices.
+    """
+    fig = make_subplots(specs=[[{"secondary_y": True}]])
+
+    fig.add_trace(
+        go.Scatter(x=egg_price_df.index, y=egg_price_df["Avg_Price"], name="Egg Price"),
+        secondary_y=False,
+    )
+
+    fig.add_trace(
+        go.Scatter(x=stock_price_df.index, y=stock_price_df["Close/Last"], name="Stock Price"),
+        secondary_y=True,
+    )
+
+    fig.update_layout(
+        title="Egg Prices vs Stock Prices",
+        xaxis_title="Date",
+        height=500,
+    )
+
+    fig.update_yaxes(title_text="Egg Price (USD)", secondary_y=False)
+    fig.update_yaxes(title_text="Stock Price (USD)", secondary_y=True)
+
+    return fig
+
 
 # === 1. EGG PRICE vs STOCK PRICE TIME SERIES ===
 def show_price_comparison(egg_df, stock_df, stock_name="Selected Stock"):
@@ -67,20 +114,19 @@ def show_bird_flu_trends():
 
 # === 3. COMBINED OVERVIEW ===
 def show_combined_dashboard():
-
-    #Loading data
+    # Loading data
     egg_df = prep_egg_price_data("egg_prices")
     calm_df, _, _ = prep_stock_price_data("calmaine")
     for col in ["Close_Last", "Open", "High", "Low"]:
         calm_df[col] = calm_df[col].replace(r'[\$,]', '', regex=True).astype(float)
     flu_df = prep_bird_flu_data("bird_flu")
 
-    #prepping birdflu
+    # Prepping bird flu
     flu_df.rename(columns={"Outbreak Date": "Date"}, inplace=True)
     flu_df = flu_df.groupby("Date")["Flock Size"].sum().reset_index()
     flu_df = flu_df.set_index("Date").resample("M").sum().reset_index()
 
-    # resample stocks
+    # Resample stocks
     calm_df = calm_df.set_index("Date").resample("M").mean().reset_index()
 
     fig = make_subplots(specs=[[{"secondary_y": True}]])
@@ -106,127 +152,3 @@ def show_combined_dashboard():
     fig.update_yaxes(title_text="Stock Price (USD)", secondary_y=True)
 
     st.plotly_chart(fig, use_container_width=True)
-
-def show_wild_bird_map(wild_bird_df, bird_flu_df):
-    """
-    Displays a cumulative-progressive map:
-    State color = chicken deaths (Sum of Flock Size)
-    Circles = wild bird infections (Sum of Wild Birds)
-    Data accumulates progressively from Jan 2022.
-    Requires https://raw.githubusercontent.com/advanced-computing/chicken_egg/main/app_data/us_states.geojson
-    """
-
-    # Cargar el GeoJSON de estados
-    url = "https://raw.githubusercontent.com/advanced-computing/chicken_egg/main/app_data/us_states.geojson"
-    response = requests.get(url)
-    geojson = response.json()
-
-    # Normalizar nombres de estado en tus datos
-    wild_df = wild_bird_df.copy()
-    flock_df = bird_flu_df.copy()
-    wild_df["State"] = wild_df["State"].str.title()
-    flock_df["State"] = flock_df["State"].str.title()
-
-    # Filtrar GeoJSON para incluir solo estados en los datasets
-    geojson_states = [f["properties"]["NAME"] for f in geojson["features"]]
-    used_states = set(wild_df["State"].unique()).union(set(flock_df["State"].unique()))
-    valid_states = sorted(set(geojson_states).intersection(used_states))
-    geojson["features"] = [f for f in geojson["features"] if f["properties"]["NAME"] in valid_states]
-
-    # Preparar columnas de mes
-    wild_df['Month'] = pd.to_datetime(wild_df['Date Detected'], errors='coerce').dt.to_period("M").dt.to_timestamp()
-    flock_df['Month'] = pd.to_datetime(flock_df['Outbreak Date'], errors='coerce').dt.to_period("M").dt.to_timestamp()
-
-    # Agrupar por mes y estado
-    wild_grouped = wild_df.groupby(['Month', 'State']).size().reset_index(name='Wild Count')
-    flock_grouped = flock_df.groupby(['Month', 'State']).agg({
-        'Flock Size': 'sum',
-        'lat': 'mean',
-        'lng': 'mean'
-    }).reset_index()
-
-    # Unir ambos
-    merged = pd.merge(flock_grouped, wild_grouped, on=['Month', 'State'], how='left')
-    merged['Wild Count'] = merged['Wild Count'].fillna(0)
-    merged['Month_str'] = merged['Month'].dt.strftime("%b %Y")
-
-    # Timeline
-    months_sorted = sorted(merged['Month'].dropna().unique())
-    month_strs = [pd.to_datetime(m).strftime("%b %Y") for m in months_sorted]
-
-    selected_label = st.select_slider("🗓️ Progressive Timeline (Cumulative to...)", options=month_strs, value=month_strs[0])
-    selected_cutoff = pd.to_datetime(selected_label)
-
-    # Acumulado hasta la fecha seleccionada
-    cumulative_view = merged[merged['Month'] <= selected_cutoff]
-
-    if cumulative_view.empty:
-        st.info("No data available up to this date.")
-        return
-
-    # Agrupar por estado acumulado
-    view = cumulative_view.groupby("State").agg({
-        "Flock Size": "sum",
-        "Wild Count": "sum",
-        "lat": "mean",
-        "lng": "mean"
-    }).reset_index()
-
-    # Hover info
-    view["Hover"] = (
-        "State: " + view["State"] +
-        "<br>Wild Infections: " + view["Wild Count"].astype(int).astype(str) +
-        "<br>Flock Deaths: " + view["Flock Size"].astype(int).astype(str)
-    )
-
-    # Pintar estados por Flock Size (choropleth)
-    fig = px.choropleth_mapbox(
-        view,
-        geojson=geojson,
-        locations="State",
-        featureidkey="properties.NAME",
-        color="Flock Size",
-        color_continuous_scale="YlOrRd",
-        range_color=(0, view["Flock Size"].max()),
-        mapbox_style="carto-darkmatter",
-        zoom=3,
-        center={"lat": 37.8, "lon": -96},
-        opacity=0.6,
-        labels={"Flock Size": "Flock Deaths"},
-        height=600
-    )
-
-    # Añadir globos por Wild Count
-    fig.add_scattermapbox(
-        lat=view["lat"],
-        lon=view["lng"],
-        mode="markers",
-        marker=px.scatter_mapbox(
-            view,
-            lat="lat",
-            lon="lng",
-            size="Wild Count",
-            size_max=50
-        ).data[0].marker,
-        text=view["State"] + "<br>Wild Cases: " + view["Wild Count"].astype(int).astype(str),
-        hoverinfo="text",
-        name="Wild Bird Infections"
-    )
-
-    fig.update_layout(
-        title=f"📍 Wild Bird Infections & Chicken Deaths – Cumulative until {selected_label}",
-        margin={"r": 0, "t": 50, "l": 0, "b": 0},
-        paper_bgcolor="#111111",
-        font_color="white",
-        legend_title_text="Chicken Deaths (State Color)",
-    )
-
-    # Descripción superior
-    st.markdown("""
-    **Map Explanation**  
-    - **State Color**: Number of chickens lost due to outbreaks (Flock Size)  
-    - **Bubble Size**: Number of wild bird infections detected  
-    - Use the slider to view how both have progressed from Jan 2022 until now.
-    """)
-
-    st.plotly_chart(fig, use_container_width=True)

app_tests/test_data_prep.py

@@ -4,12 +4,14 @@
 from app_modules.functions_app import (
     prep_bird_flu_data,
     prep_egg_price_data,
-    prep_stock_price_data
+    prep_stock_price_data,
+    prep_wild_bird_data,  # Added import for prep_wild_bird_data
 )
 from app_tests.test_helper_data_prep import (
     create_stock_ex,
     create_egg_price_ex,
     create_bird_flu_ex,
+    create_wild_bird_ex,  # Added import for create_wild_bird_ex
 )
 
 @pytest.mark.parametrize(
@@ -18,6 +20,7 @@
         (prep_stock_price_data, pd.DataFrame({"Open": [100, 101, 102]}), KeyError),  # Missing 'Close/Last'
         (prep_egg_price_data, pd.DataFrame({"Price": [2.5, 3.0, 3.2]}), ValueError),  # Missing 'Year'
         (prep_bird_flu_data, pd.DataFrame({"Flock Size": [10, 20]}), KeyError),  # Missing 'State'
+        (prep_wild_bird_data, pd.DataFrame({"County": ["A", "B"]}), KeyError),  # Missing 'State'
     ]
 )
 def test_prep_functions_raise_errors(func, df, expected_exception):
@@ -51,3 +54,20 @@ def test_bird_flu_flock_size_is_numeric():
     bird_flu_df = pd.read_csv(StringIO(create_bird_flu_ex()))
     df = prep_bird_flu_data(bird_flu_df)
     assert pd.api.types.is_numeric_dtype(df["Flock Size"]), "Flock Size should be numeric."
+
+def test_wild_bird_data_has_lat_lng():
+    """
+    Test that prep_wild_bird_data returns a DataFrame with 'lat' and 'lng' columns.
+    """
+    wild_bird_df = pd.read_csv(StringIO(create_wild_bird_ex()))
+    df = prep_wild_bird_data(wild_bird_df)
+    assert "lat" in df.columns, "DataFrame must have 'lat' column."
+    assert "lng" in df.columns, "DataFrame must have 'lng' column."
+
+def test_wild_bird_data_missing_columns():
+    """
+    Test that prep_wild_bird_data raises an error if required columns are missing.
+    """
+    wild_bird_df = pd.DataFrame({"County": ["A", "B"]})  # Missing 'State'
+    with pytest.raises(KeyError):
+        prep_wild_bird_data(wild_bird_df)

app_tests/test_helper_data_prep.py

@@ -25,3 +25,13 @@ def create_bird_flu_ex():
 Alabama,Montgomery,1000,32.3668052,-86.2999689
 Georgia,Clarke,2000,33.9519347,-83.357567
 """
+
+def create_wild_bird_ex():
+    """
+    Returns example data similar to wild bird data
+    """
+    return """State,County,Observation Count,lat,lng
+Alabama,Montgomery,50,32.3668052,-86.2999689
+Georgia,Clarke,75,33.9519347,-83.357567
+Florida,Miami-Dade,100,25.7616798,-80.1917902
+"""

app_tests/test_viz.py

@@ -1,6 +1,14 @@
 import pytest
 import pandas as pd
-from app_modules.visualizations_app import create_geospatial, create_time_series
+from app_modules.visualizations_app import (
+    create_geospatial,
+    create_time_series,
+    show_price_comparison,
+    show_bird_flu_trends,
+    show_combined_dashboard,
+)
+import streamlit as st
+
 
 def test_create_geospatial():
     sample_data = pd.DataFrame({
@@ -13,6 +21,7 @@ def test_create_geospatial():
 
     assert fig and len(fig.data) > 0, "Geospatial plot should contain data points."
 
+
 def test_create_time_series():
     egg_price_df = pd.DataFrame({
         'Date': pd.date_range(start='2020-01-01', periods=5),
@@ -27,3 +36,61 @@ def test_create_time_series():
     fig = create_time_series(egg_price_df, stock_price_df)
 
     assert fig and len(fig.data) == 2, "Time series should contain two lines."
+
+
+def test_show_price_comparison(mocker):
+    egg_price_df = pd.DataFrame({
+        'Date': pd.date_range(start='2020-01-01', periods=5),
+        'Avg_Price': [1, 2, 3, 4, 5]
+    }).set_index('Date')
+
+    stock_price_df = pd.DataFrame({
+        'Date': pd.date_range(start='2020-01-01', periods=5),
+        'Close_Last': [10, 20, 30, 40, 50]
+    })
+
+    mocker.patch("streamlit.plotly_chart")  # Mock Streamlit's plotly_chart
+    show_price_comparison(egg_price_df, stock_price_df, stock_name="Test Stock")
+
+    st.plotly_chart.assert_called_once()  # Ensure the chart was rendered
+
+
+def test_show_bird_flu_trends(mocker):
+    mocker.patch("app_modules.visualizations_app.prep_bird_flu_data", return_value=pd.DataFrame({
+        'Outbreak Date': pd.date_range(start='2020-01-01', periods=5),
+        'Flock Size': [10, 20, 30, 40, 50]
+    }))
+
+    mocker.patch("streamlit.plotly_chart")  # Mock Streamlit's plotly_chart
+    show_bird_flu_trends()
+
+    st.plotly_chart.assert_called_once()  # Ensure the chart was rendered
+
+
+def test_show_combined_dashboard(mocker):
+    mocker.patch("app_modules.visualizations_app.prep_egg_price_data", return_value=pd.DataFrame({
+        'Date': pd.date_range(start='2020-01-01', periods=5),
+        'Avg_Price': [1, 2, 3, 4, 5]
+    }))
+
+    mocker.patch("app_modules.visualizations_app.prep_stock_price_data", return_value=(
+        pd.DataFrame({
+            'Date': pd.date_range(start='2020-01-01', periods=5),
+            'Close_Last': [10, 20, 30, 40, 50],
+            'Open': [5, 15, 25, 35, 45],
+            'High': [15, 25, 35, 45, 55],
+            'Low': [0, 10, 20, 30, 40]
+        }),
+        None,
+        None
+    ))
+
+    mocker.patch("app_modules.visualizations_app.prep_bird_flu_data", return_value=pd.DataFrame({
+        'Outbreak Date': pd.date_range(start='2020-01-01', periods=5),
+        'Flock Size': [10, 20, 30, 40, 50]
+    }))
+
+    mocker.patch("streamlit.plotly_chart")  # Mock Streamlit's plotly_chart
+    show_combined_dashboard()
+
+    st.plotly_chart.assert_called()  # Ensure charts were rendered