Map pdfm features

Mapping PDFM Features and Predicted Housing Prices

Useful Resources¶

• Google's Population Dynamics Foundation Model (PDFM)
• Request access to PDFM embeddings here
• Zillow data can be accessed here

Installation¶

Uncomment and run the following cell to install the required libraries.

In [ ]:

# %pip install "leafmap[maplibre]" scikit-learn

# %pip install "leafmap[maplibre]" scikit-learn

Import Libraries¶

In [ ]:

import os
import pandas as pd
import geopandas as gpd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.neighbors import KNeighborsRegressor
from leafmap.common import evaluate_model, plot_actual_vs_predicted, download_file
import leafmap.maplibregl as leafmap

import os import pandas as pd import geopandas as gpd from sklearn.model_selection import train_test_split from sklearn.linear_model import LinearRegression from sklearn.neighbors import KNeighborsRegressor from leafmap.common import evaluate_model, plot_actual_vs_predicted, download_file import leafmap.maplibregl as leafmap

Download Zillow Data¶

Download the Zillow home value data at the county level.

In [ ]:

zhvi_url = "https://github.com/opengeos/datasets/releases/download/us/zillow_home_value_index_by_county.csv"
zhvi_file = "data/zillow_home_value_index_by_county.csv"

zhvi_url = "https://github.com/opengeos/datasets/releases/download/us/zillow_home_value_index_by_county.csv" zhvi_file = "data/zillow_home_value_index_by_county.csv"

In [ ]:

if not os.path.exists(zhvi_file):
    download_file(zhvi_url, zhvi_file)

if not os.path.exists(zhvi_file): download_file(zhvi_url, zhvi_file)

Process Zillow Data¶

In [ ]:

zhvi_df = pd.read_csv(
    zhvi_file, dtype={"StateCodeFIPS": "string", "MunicipalCodeFIPS": "string"}
)
zhvi_df.index = "geoId/" + zhvi_df["StateCodeFIPS"] + zhvi_df["MunicipalCodeFIPS"]
zhvi_df.head()

zhvi_df = pd.read_csv( zhvi_file, dtype={"StateCodeFIPS": "string", "MunicipalCodeFIPS": "string"} ) zhvi_df.index = "geoId/" + zhvi_df["StateCodeFIPS"] + zhvi_df["MunicipalCodeFIPS"] zhvi_df.head()

Request access to PDFM Embeddings¶

To request access to PDFM embeddings, please follow the instructions here.

In [ ]:

county_geojson = "data/county.geojson"
if not os.path.exists(county_geojson):
    raise FileNotFoundError("Please request the embeddings from Google")

county_geojson = "data/county.geojson" if not os.path.exists(county_geojson): raise FileNotFoundError("Please request the embeddings from Google")

Load county boundaries¶

In [ ]:

county_gdf = gpd.read_file(county_geojson)
county_gdf.set_index("place", inplace=True)
county_gdf.head()

county_gdf = gpd.read_file(county_geojson) county_gdf.set_index("place", inplace=True) county_gdf.head()

Join home value data and county boundaries¶

In [ ]:

df = zhvi_df.join(county_gdf)
zhvi_gdf = gpd.GeoDataFrame(df, geometry="geometry")
zhvi_gdf.head()

df = zhvi_df.join(county_gdf) zhvi_gdf = gpd.GeoDataFrame(df, geometry="geometry") zhvi_gdf.head()

In [ ]:

column = "2024-10-31"
gdf = zhvi_gdf[["RegionName", "State", column, "geometry"]]
gdf.head()

column = "2024-10-31" gdf = zhvi_gdf[["RegionName", "State", column, "geometry"]] gdf.head()

Visualize home values in 2D¶

In [ ]:

m = leafmap.Map(style="liberty")
first_symbol_id = m.find_first_symbol_layer()["id"]
m.add_data(
    gdf,
    cmap="Blues",
    column=column,
    legend_title="Median Home Value",
    name="Median Home Value",
    before_id=first_symbol_id,
)
m.add_layer_control()
m

m = leafmap.Map(style="liberty") first_symbol_id = m.find_first_symbol_layer()["id"] m.add_data( gdf, cmap="Blues", column=column, legend_title="Median Home Value", name="Median Home Value", before_id=first_symbol_id, ) m.add_layer_control() m

Visualize home values in 3D¶

In [ ]:

m = leafmap.Map(style="liberty", pitch=60)
m.add_data(
    gdf,
    cmap="Blues",
    column=column,
    legend_title="Median Home Value",
    extrude=True,
    scale_factor=3,
    before_id=first_symbol_id,
    name="Median Home Value",
)
m.add_layer_control()
m

m = leafmap.Map(style="liberty", pitch=60) m.add_data( gdf, cmap="Blues", column=column, legend_title="Median Home Value", extrude=True, scale_factor=3, before_id=first_symbol_id, name="Median Home Value", ) m.add_layer_control() m

Load PDFM county embeddings¶

In [ ]:

embeddings_file_path = "data/county_embeddings.csv"

embeddings_file_path = "data/county_embeddings.csv"

In [ ]:

embeddings_df = pd.read_csv(embeddings_file_path).set_index("place")
embeddings_df.head()

embeddings_df = pd.read_csv(embeddings_file_path).set_index("place") embeddings_df.head()

In [ ]:

df = embeddings_df.join(county_gdf)
embeddings_gdf = gpd.GeoDataFrame(df, geometry="geometry")
embeddings_gdf.head()

df = embeddings_df.join(county_gdf) embeddings_gdf = gpd.GeoDataFrame(df, geometry="geometry") embeddings_gdf.head()

Visualize PDFM features¶

Select any of the 329 PDFM features to visualize.

In [ ]:

column = "feature329"  # Change this to the feature you want to use
gdf = embeddings_gdf[[column, "state", "county", "geometry"]]
gdf.head()

column = "feature329" # Change this to the feature you want to use gdf = embeddings_gdf[[column, "state", "county", "geometry"]] gdf.head()

In [ ]:

m = leafmap.Map(style="liberty")
m.add_data(
    gdf,
    cmap="Blues",
    column=column,
    legend_title=column,
    before_id=first_symbol_id,
    name=column,
)
m.add_layer_control()
m

m = leafmap.Map(style="liberty") m.add_data( gdf, cmap="Blues", column=column, legend_title=column, before_id=first_symbol_id, name=column, ) m.add_layer_control() m

In [ ]:

m = leafmap.Map(style="liberty", pitch=60)
m.add_data(
    gdf,
    cmap="Blues",
    column=column,
    legend_title=column,
    before_id=first_symbol_id,
    name=column,
    extrude=True,
    scale_factor=0.00005,
)
m.add_layer_control()
m

m = leafmap.Map(style="liberty", pitch=60) m.add_data( gdf, cmap="Blues", column=column, legend_title=column, before_id=first_symbol_id, name=column, extrude=True, scale_factor=0.00005, ) m.add_layer_control() m

Join Zillow and PDFM Data¶

In [ ]:

data = zhvi_df.join(embeddings_df, how="inner")
data.head()

data = zhvi_df.join(embeddings_df, how="inner") data.head()

In [ ]:

embedding_features = [f"feature{x}" for x in range(330)]
label = "2024-10-31"  # Change this to the date you want to predict

embedding_features = [f"feature{x}" for x in range(330)] label = "2024-10-31" # Change this to the date you want to predict

In [ ]:

data = data.dropna(subset=[label])

data = data.dropna(subset=[label])

Split Train and Test Data¶

In [ ]:

data = data[embedding_features + [label]]
X = data[embedding_features]
y = data[label]

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42
)

data = data[embedding_features + [label]] X = data[embedding_features] y = data[label] X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.2, random_state=42 )

Fit Linear Regression Model¶

In [ ]:

model = LinearRegression()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)

model = LinearRegression() model.fit(X_train, y_train) y_pred = model.predict(X_test)

Evaluate Linear Regression Model¶

In [ ]:

evaluation_df = pd.DataFrame({"y": y_test, "y_pred": y_pred})
metrics = evaluate_model(evaluation_df)
print(metrics)

evaluation_df = pd.DataFrame({"y": y_test, "y_pred": y_pred}) metrics = evaluate_model(evaluation_df) print(metrics)

In [ ]:

xy_lim = (0, 1_000_000)
plot_actual_vs_predicted(
    evaluation_df,
    xlim=xy_lim,
    ylim=xy_lim,
    title="Actual vs Predicted Home Values",
    x_label="Actual Home Value",
    y_label="Predicted Home Value",
)

xy_lim = (0, 1_000_000) plot_actual_vs_predicted( evaluation_df, xlim=xy_lim, ylim=xy_lim, title="Actual vs Predicted Home Values", x_label="Actual Home Value", y_label="Predicted Home Value", )

Join predicted values with county boundaries¶

In [ ]:

df = evaluation_df.join(gdf)
df["difference"] = df["y_pred"] - df["y"]
evaluation_gdf = gpd.GeoDataFrame(df, geometry="geometry")
evaluation_gdf.drop(columns=["category", "color", column], inplace=True)
evaluation_gdf.head()

df = evaluation_df.join(gdf) df["difference"] = df["y_pred"] - df["y"] evaluation_gdf = gpd.GeoDataFrame(df, geometry="geometry") evaluation_gdf.drop(columns=["category", "color", column], inplace=True) evaluation_gdf.head()

Visualize actual home values¶

In [ ]:

m = leafmap.Map(style="liberty", pitch=60)
m.add_data(
    evaluation_gdf,
    cmap="Blues",
    column="y",
    legend_title="Actual Home Value",
    before_id=first_symbol_id,
    name="Actual Home Value",
    extrude=True,
    scale_factor=3,
)
m.add_layer_control()
m

m = leafmap.Map(style="liberty", pitch=60) m.add_data( evaluation_gdf, cmap="Blues", column="y", legend_title="Actual Home Value", before_id=first_symbol_id, name="Actual Home Value", extrude=True, scale_factor=3, ) m.add_layer_control() m

Visualize predicted home values¶

In [ ]:

m = leafmap.Map(style="liberty", pitch=60)
m.add_data(
    evaluation_gdf,
    cmap="Blues",
    column="y_pred",
    legend_title="Predicted Home Value",
    before_id=first_symbol_id,
    name="Predicted Home Value",
    extrude=True,
    scale_factor=3,
)
m.add_layer_control()
m

m = leafmap.Map(style="liberty", pitch=60) m.add_data( evaluation_gdf, cmap="Blues", column="y_pred", legend_title="Predicted Home Value", before_id=first_symbol_id, name="Predicted Home Value", extrude=True, scale_factor=3, ) m.add_layer_control() m

Visualize difference between predicted and actual home values¶

In [ ]:

m = leafmap.Map(style="liberty", pitch=60)
m.add_data(
    evaluation_gdf,
    cmap="coolwarm",
    column="difference",
    legend_title="y_pred-y",
    before_id=first_symbol_id,
    name="Difference",
    extrude=True,
    scale_factor=3,
)
m.add_layer_control()
m

m = leafmap.Map(style="liberty", pitch=60) m.add_data( evaluation_gdf, cmap="coolwarm", column="difference", legend_title="y_pred-y", before_id=first_symbol_id, name="Difference", extrude=True, scale_factor=3, ) m.add_layer_control() m