GEE python 使用gee colab进行指定研究区的平均值、最大值、最小值等

使用colab之前一定要进行下面代码的加载：
安装 Earth Engine API 和 geemap
安装 Earth Engine Python API 和 geemap。 geemap Python 包基于 ipyleaflet 和 folium 包构建，并实现了与 Earth Engine 数据层交互的多种方法，例如 Map.addLayer()、Map.setCenter() 和 Map.centerObject()。 以下脚本检查 geemap 软件包是否已安装。 如果没有，它将安装 geemap，它会自动安装其依赖项，包括 Earthengine-api、folium 和 ipyleaflet。

# Installs geemap package
import subprocess

try:
    import geemap
except ImportError:
    print('Installing geemap ...')
    subprocess.check_call(["python", '-m', 'pip', 'install', 'geemap'])

import ee
import geemap

真彩色影像加载如下面的代码所示：
这里就是我们加载影像，然后使用中位数合成，然后限定至少5景影像，然后就是对影像可是参数的设定，然后就是设定地图中心点和进行地图的加载。

# Add Earth Engine dataset
# Load a Landsat 8 collection.
collection = ee.ImageCollection('LANDSAT/LC08/C01/T1') \
    .filterBounds(ee.Geometry.Point(-122.262, 37.8719)) \
    .filterDate('2014-01-01', '2014-12-31') \
    .sort('CLOUD_COVER')

# Compute the median of each pixel for each band of the 5 least cloudy scenes.
median = collection.limit(5).reduce(ee.Reducer.median())

# Define visualization parameters in an object literal.
vizParams = {'bands': ['B5_median', 'B4_median', 'B3_median'],
             'min': 5000, 'max': 15000, 'gamma': 1.3}

Map.setCenter(-122.262, 37.8719, 10)
Map.addLayer(median, vizParams, 'Median image')

这里加载完单景影像，然后设定我们的研究区，然后加载矢量，

# Add Earth Engine dataset
# Load and display a Landsat TOA image.
image = ee.Image('LANDSAT/LC08/C01/T1_TOA/LC08_044034_20140318')
Map.addLayer(image, {'bands': ['B4', 'B3', 'B2'], 'max': 0.3}, 'Landsat 8')

# Create an arbitrary rectangle as a region and display it.
region = ee.Geometry.Rectangle(-122.2806, 37.1209, -122.0554, 37.2413)
Map.centerObject(ee.FeatureCollection(region), 13)
Map.addLayer(ee.Image().paint(region, 0, 2), {}, 'Region')

# Get a dictionary of means in the region.  Keys are bandnames.
mean = image.reduceRegion(**{
  'reducer': ee.Reducer.mean(),
  'geometry': region,
  'scale': 30
})

print(mean.getInfo())

这里函数：
**image.reduceRegion(*args, kwargs)
Apply a reducer to all the pixels in a specific region. Either the reducer
must have the same number of inputs as the input image has bands, or it
must have a single input and will be repeated for each band. Returns a
dictionary of the reducer’s outputs.
将缩减器应用于特定区域中的所有像素。 无论是减速机
输入的数量必须与输入图像的带数相同，否则
必须有一个输入，并且将为每个频段重复。 返回一个
减速器输出的字典。
Args:
image: The image to reduce.
reducer: The reducer to apply.
geometry: The region over which to reduce data. Defaults to
the footprint of the image’s first band.
scale: A nominal scale in meters of the projection to work in.
crs: The projection to work in. If unspecified, the projection of
the image’s first band is used. If specified in addition to
scale, rescaled to the specified scale.
crsTransform: The list of CRS transform values. This is
a row-major ordering of the 3x2 transform matrix.
This option is mutually exclusive with ‘scale’, and
replaces any transform already set on the projection.
bestEffort: If the polygon would contain too many pixels at
the given scale, compute and use a larger scale which
would allow the operation to succeed.
maxPixels: The maximum number of pixels to reduce.
tileScale: A scaling factor between 0.1 and 16 used to
adjust aggregation tile size; setting a larger tileScale
(e.g. 2 or 4) uses smaller tiles and may enable
computations that run out of memory with the default.
image：要缩小的图像。
减速器：要应用的减速器。
几何：要减少数据的区域。 默认为
图像第一条带的足迹。
比例：要使用的投影的标称比例（以米为单位）。
crs：要使用的投影。如果未指定，则投影
使用图像的第一个波段。 如果除了指定
缩放，重新缩放到指定的缩放比例。
crsTransform：CRS 变换值的列表。 这是
3x2 变换矩阵的行优先顺序。
此选项与“scale”互斥，并且
替换投影上已设置的任何变换。
bestEffort：如果多边形在以下位置包含太多像素
给定的比例，计算并使用更大的比例
将使操作成功。
maxPixels：要减少的最大像素数。
tileScale：0.1 到 16 之间的缩放因子，用于
调整聚合图块大小； 设置更大的tileScale
（例如 2 或 4）使用较小的图块并且可以启用
默认情况下内存不足的计算。

最后的结果：
{‘B1’: 0.10156660976055135, ‘B10’: 288.38945983522234, ‘B11’: 287.449363371539, ‘B2’: 0.0777191134617773, ‘B3’: 0.05530029791297399, ‘B4’: 0.036708278784827325, ‘B5’: 0.2213974520811337, ‘B6’: 0.07888247177758294, ‘B7’: 0.03508945487734233, ‘B8’: 0.04710008874158145, ‘B9’: 0.0015609697454817123, ‘BQA’: 2720.119445772292}
{‘B1’: 0.10057091121347973, ‘B10’: 288.31267832028374, ‘B11’: 287.4380035810285, ‘B2’: 0.0770883840019017, ‘B3’: 0.05370450386558887, ‘B4’: 0.03416041768795379, ‘B5’: 0.22070476984580337, ‘B6’: 0.07128097690030873, ‘B7’: 0.028315342903770746, ‘B8’: 0.04588400150438728, ‘B9’: 0.0014895948115736248, ‘BQA’: 2720.0000000000396}
{‘B1’: 0.09194143861532211, ‘B10’: 282.551513671875, ‘B11’: 282.04803466796875, ‘B2’: 0.0669216737151146, ‘B3’: 0.03696415200829506, ‘B4’: 0.02074405923485756, ‘B5’: 0.010509952902793884, ‘B6’: 0.0009378909599035978, ‘B7’: 0.0006896242848597467, ‘B8’: 0.030233364552259445, ‘B9’: -2.7590731406235136e-05, ‘BQA’: 2720}
{‘B1’: 0.09194143861532211, ‘B10’: 282.551513671875, ‘B11’: 282.04803466796875, ‘B2’: 0.0669216737151146, ‘B3’: 0.03696415200829506, ‘B4’: 0.02074405923485756, ‘B5’: 0.010509952902793884, ‘B6’: 0.0009378909599035978, ‘B7’: 0.0006896242848597467, ‘B8’: 0.030233364552259445, ‘B9’: -2.7590731406235136e-05, ‘BQA’: 2720}
{‘B10_max’: 302.4209289550781, ‘B10_min’: 282.551513671875, ‘B11_max’: 300.42791748046875, ‘B11_min’: 282.04803466796875, ‘B1_max’: 0.42826008796691895, ‘B1_min’: 0.09194143861532211, ‘B2_max’: 0.43499088287353516, ‘B2_min’: 0.0669216737151146, ‘B3_max’: 0.44122514128685, ‘B3_min’: 0.03696415200829506, ‘B4_max’: 0.4735274016857147, ‘B4_min’: 0.02074405923485756, ‘B5_max’: 0.5558140277862549, ‘B5_min’: 0.010509952902793884, ‘B6_max’: 0.4359287917613983, ‘B6_min’: 0.0009378909599035978, ‘B7_max’: 0.3699174225330353, ‘B7_min’: 0.0006896242848597467, ‘B8_max’: 0.4776651859283447, ‘B8_min’: 0.030233364552259445, ‘B9_max’: 0.005710129160434008, ‘B9_min’: -2.7590731406235136e-05, ‘BQA_max’: 2976, ‘BQA_min’: 2720}

方差标准差自己可以通过上面的函数进行加载，然后进行计算。这里我们输入ee.Reducer.后后面会自动给你提示相应的函数，然后你直接点击后就可以直接加载，这个相较于JavaScript中的函数没有提示的结果还是非常好的。