问如何计算人口与土地覆盖类型百分比之间的Pearson相关系数(r)？
EN

Stack Overflow用户

提问于 2018-12-11 11:19:09

回答 1查看 304关注 0票数 0

下面的代码输出的似乎是每个普查区域的字典列表，这基本上是一个指定的土地区域。我能够计算出人口和几种不同的土地覆盖类型的百分比。现在我要计算人口与每一种土地覆盖类型的百分比之间的Pearson相关系数。

我要做的是提取/过滤字典列表，这样我就可以将人口与每一种土地覆盖类型进行比较。因此，皮尔逊相关性：

人口和发达土地
人口和贫瘠土地
人口和林地
..。

以下是代码：

import geopandas as gpd
from rasterstats import zonal_stats
from rasterio.mask import mask
from rasterio.plot import show
import matplotlib.pyplot as plt
import numpy as np
import fiona
import rasterio
from scipy import stats
from rasterio.warp import calculate_default_transform, reproject, Resampling

mass_fp = r"New_Massachusetts.tif"

mass_tracts = gpd.read_file("Massachusetts/Massachusetts.shp");
dst_crs = 'EPSG:4269';


with rasterio.open('Massachusetts.tif') as src:
    transform, width, height = calculate_default_transform(
        src.crs, mass_tracts.crs, src.width, src.height, *src.bounds)
    kwargs = src.meta.copy()
    kwargs.update({
        'crs': mass_tracts.crs,
        'transform': transform,
        'width': width,
        'height': height
    })

    with rasterio.open('New_Mass.tif', 'w', **kwargs) as dst:
        for i in range(1, src.count + 1):
            reproject(
                source=rasterio.band(src, i),
                destination=rasterio.band(dst, i),
                src_transform=src.transform,
                src_crs=src.crs,
                dst_transform=transform,
                dst_crs=dst_crs,
                resampling=Resampling.nearest)



#Getting zonal stats
stats = zonal_stats("Massachusetts/Massachusetts.shp", "New_Mass.tif",stats="count",geojson_out=True, copy_properties=True,nodata_value=0,categorical=True);

#Variables for our loop below
total_pop=0.0;
total_pixel_count=0.0;
total_developed = 0.0;
total_water_ice = 0.0;
total_barren_land = 0.0;
total_forest = 0.0;

#Array to store our census track
census_tract_land_percentages = [];

#Looping through each tract in the stats data and getting the data we need and then storing it in a array with dictionaries
#[11,12], [21, 22, 23,24], 31, [41,42,43] 5 

for x in stats:
    total_pixel_count=x["properties"]["count"];
    total_census_population = x["properties"]["DP0010001"]
    total_developed= (float(x["properties"].get(21,0)+x.get(22,0)+x["properties"].get(23,0) + x["properties"].get(24,0))/total_pixel_count)*100;
    total_water_ice = (float(x["properties"].get(11,0)+x["properties"].get(12,0))/total_pixel_count)*100;
    total_barren_land=float(x["properties"].get(31,0)/total_pixel_count)*100;
    total_forest = (float(x["properties"].get(41,0)+x["properties"].get(42,0)+x["properties"].get(43,0))/total_pixel_count)*100;

    census_tract_land_percentages.append({"Total Population:":total_census_population,"Total Water Ice Cover":total_water_ice,"Total Developed":total_developed,
                                         "Total Barren Land":total_barren_land,"Total Forest":total_forest});

print(census_tract_land_percentages);

#Getting the total population for all census tracts
for x in mass_tracts["DP0010001"]:
    total_pop+=x

np_census_arr = np.asarray(census_tract_land_percentages);

一旦运行这段代码，我将得到以下字典列表，我想知道如何提取/过滤出人口，并将其与每一个土地覆盖百分比进行比较，并最终计算Pearson r相关性。

[{'Total Population:': 4585, 'Total Water Ice Cover': 2.848142234497044, 'Total Developed': 17.205368316575324, 'Total Barren Land': 0.22439908514219134, 'Total Forest': 34.40642126612868},

 {'Total Population:': 4751, 'Total Water Ice Cover': 1.047783534830167, 'Total Developed': 37.27115716753022, 'Total Barren Land': 0.11514104778353484, 'Total Forest': 19.11341393206678},

 {'Total Population:': 3214, 'Total Water Ice Cover': 0.09166603009701321, 'Total Developed': 23.50469788404247, 'Total Barren Land': 0.2597204186082041, 'Total Forest': 20.418608204109695},

 {'Total Population:': 5005, 'Total Water Ice Cover': 0.0, 'Total Developed': 66.37545713124746, 'Total Barren Land': 0.0, 'Total Forest': 10.68671271840715},

...
]

有什么想法吗?我怎样才能通过这个循环，然后根据每一种土地覆盖类型的百分比计算出整个人口变量的Pearson r？

谢谢

python

pandas

pearson-correlation

rasterio

语音识别特惠，低至14.9元！

提供业界非常具有性价比的语音识别服务，超高识别准确率，适用多场景

回答 1

Stack Overflow用户

发布于 2018-12-11 11:51:31

xs = []
y1s = []
y2s = []
y3s = []
y4s = []

for entry in entries:
    xs.append(entry['population'])
    ice = entry['Total Water Ice Cover']
    dev = entry['Total Developed']
    bar = entry['Total Barren Land']
    forest = entry['Total Forest']

    total_land = ice+dev+bar+forest
    y1s.append(ice/total_land)
    y2s.append(dev/total_land)
    y3s.append(bar/total_land)
    y4s.append(forest/total_land)



print(scipy.stats.pearsonr(xs,y1s)," = ICE") 
...