NikaNotebook

import geopandas as gpd
import pandas as pd
from shapely.geometry import Point, Polygon
from shapely.ops import voronoi_diagram
import folium

# Buffer analysis - Create 1km buffers around points
points_gdf = gpd.read_file('points.geojson')
buffers = points_gdf.geometry.buffer(1000)  # 1000 meters

# Intersection operations - Find overlapping areas
layer1 = gpd.read_file('layer1.geojson')
layer2 = gpd.read_file('layer2.geojson')
overlaps = gpd.overlay(layer1, layer2, how='intersection')

# Distance calculations - Calculate distances between features
points = gpd.read_file('points.geojson')
polygons = gpd.read_file('polygons.geojson')
distances = points.geometry.apply(lambda x: polygons.geometry.distance(x).min())

# Spatial joins - Join attributes based on location
joined = gpd.sjoin(points, polygons, how='left', predicate='within')

# Voronoi diagrams - Create service areas
from scipy.spatial import Voronoi
import numpy as np
coords = np.array([[p.x, p.y] for p in points.geometry])
voronoi = Voronoi(coords)

import numpy as np
from scipy import stats
import pandas as pd
from libpysal.weights import Queen
from esda.moran import Moran

# Descriptive statistics for spatial data
stats = spatial_data[['population', 'area']].describe()

# Spatial autocorrelation - Moran's I test
w = Queen.from_dataframe(spatial_data)
morans_i = Moran(spatial_data['value'], w)

# Hot spot analysis - Getis-Ord Gi* statistic
from esda.getisord import G_Local
g_local = G_Local(spatial_data['crime_rate'], w)
hotspots = spatial_data[g_local.p_sim < 0.05]

# Regression analysis with spatial variables
from sklearn.linear_model import LinearRegression
X = spatial_data[['distance_to_center', 'area']]
y = spatial_data['price']
model = LinearRegression().fit(X, y)

from sklearn.cluster import KMeans
from sklearn.ensemble import RandomForestClassifier
from sklearn.preprocessing import StandardScaler
import pandas as pd

# Spatial clustering - Group similar locations
coords = spatial_data[['longitude', 'latitude']].values
kmeans = KMeans(n_clusters=5, random_state=42)
clusters = kmeans.fit_predict(coords)

# Classification - Predict land use from satellite imagery
X = raster_data.reshape(-1, raster_data.shape[-1])
y = training_points['land_use']
rf = RandomForestClassifier(n_estimators=100, random_state=42)
rf.fit(X, y)
land_use_pred = rf.predict(X)

# Time series analysis - Analyze temporal patterns
data['date'] = pd.to_datetime(data['date'])
monthly_trends = data.groupby(data['date'].dt.to_period('M'))['temperature'].mean()

# Anomaly detection - Find unusual spatial patterns
from sklearn.ensemble import IsolationForest
iso_forest = IsolationForest(contamination=0.1, random_state=42)
anomalies = iso_forest.fit_predict(spatial_data[['value1', 'value2']])