{ "cells": [ { "cell_type": "code", "execution_count": 34, "id": "initial_id", "metadata": { "collapsed": true, "ExecuteTime": { "end_time": "2024-06-11T06:41:37.671133500Z", "start_time": "2024-06-11T06:41:37.652982600Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "['./data/iowa.nc']\n" ] } ], "source": [ "import numpy as np\n", "import netCDF4 as nc\n", "import os\n", "import pandas as pd\n", "import datetime as dt\n", "nc_path = \"./data/\"\n", "nc_files = [f\"{nc_path}{x}\" for x in os.listdir(nc_path) if x.endswith('.nc')]\n", "print(nc_files)" ] }, { "cell_type": "code", "execution_count": 35, "outputs": [], "source": [ "stations = pd.read_csv('./data/station.csv')\n", "stations.head()\n", "stations.dropna(inplace=True)" ], "metadata": { "collapsed": false, "ExecuteTime": { "end_time": "2024-06-11T06:41:37.722796200Z", "start_time": "2024-06-11T06:41:37.663028100Z" } }, "id": "9c4ed0ec8dc7ff7d" }, { "cell_type": "code", "execution_count": 36, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "['longitude', 'latitude', 'time', 't2m']\n" ] } ], "source": [ "nc_data = nc.Dataset(nc_files[0]) # 读文件\n", "print(list(nc_data.variables.keys())) # keys" ], "metadata": { "collapsed": false, "ExecuteTime": { "end_time": "2024-06-11T06:41:37.730197500Z", "start_time": "2024-06-11T06:41:37.678192900Z" } }, "id": "a88ddc29d8fa3d06" }, { "cell_type": "code", "execution_count": 37, "outputs": [ { "data": { "text/plain": "(13, 31)" }, "execution_count": 37, "metadata": {}, "output_type": "execute_result" } ], "source": [ "lat = np.asarray(nc_data['latitude'][:]).tolist()\n", "lon = np.asarray(nc_data['longitude'][:]).tolist()\n", "len(lat), len(lon)" ], "metadata": { "collapsed": false, "ExecuteTime": { "end_time": "2024-06-11T06:41:37.730197500Z", "start_time": "2024-06-11T06:41:37.693749900Z" } }, "id": "4ec1510ef5baa4b9" }, { "cell_type": "code", "execution_count": 38, "outputs": [ { "data": { "text/plain": "array([1016832, 1016833, 1016834, ..., 1025613, 1025614, 1025615])" }, "execution_count": 38, "metadata": {}, "output_type": "execute_result" } ], "source": [ "np.asarray(nc_data['time'][:])" ], "metadata": { "collapsed": false, "ExecuteTime": { "end_time": "2024-06-11T06:41:37.731222200Z", "start_time": "2024-06-11T06:41:37.710255800Z" } }, "id": "9e1cfd59ea63dee" }, { "cell_type": "code", "execution_count": 39, "outputs": [ { "data": { "text/plain": "\nint32 time(time)\n units: hours since 1900-01-01 00:00:00.0\n long_name: time\n calendar: gregorian\nunlimited dimensions: \ncurrent shape = (8784,)\nfilling on, default _FillValue of -2147483647 used" }, "execution_count": 39, "metadata": {}, "output_type": "execute_result" } ], "source": [ "nc_data['time']" ], "metadata": { "collapsed": false, "ExecuteTime": { "end_time": "2024-06-11T06:41:37.739215300Z", "start_time": "2024-06-11T06:41:37.723796300Z" } }, "id": "305b595052773792" }, { "cell_type": "code", "execution_count": 40, "outputs": [ { "data": { "text/plain": "datetime.datetime(1900, 1, 1, 0, 0)" }, "execution_count": 40, "metadata": {}, "output_type": "execute_result" } ], "source": [ "start_date = dt.datetime(1900, 1, 1)\n", "start_date" ], "metadata": { "collapsed": false, "ExecuteTime": { "end_time": "2024-06-11T06:41:37.788384900Z", "start_time": "2024-06-11T06:41:37.739215300Z" } }, "id": "9dc1b63dbd6e5847" }, { "cell_type": "code", "execution_count": 41, "outputs": [ { "data": { "text/plain": "array([[[267.10449818, 266.56524854, 265.81574602, ..., 266.35826383,\n 266.94435738, 267.10231939],\n [266.75916053, 266.21773211, 265.4017766 , ..., 266.49334859,\n 267.59908269, 267.86380524],\n [266.70360148, 265.86258993, 265.06733289, ..., 266.6197182 ,\n 267.66117811, 267.95640366],\n ...,\n [270.23759303, 270.20055367, 269.91731143, ..., 270.11231282,\n 269.99683714, 269.90750689],\n [271.34223774, 271.32153927, 271.25726507, ..., 270.55569585,\n 270.37376718, 270.24086121],\n [271.76274352, 271.85643134, 271.79215714, ..., 271.32371806,\n 270.86617291, 270.71583665]],\n\n [[267.45746158, 267.17966631, 266.73846206, ..., 266.19376546,\n 266.66983029, 266.83541806],\n [267.5337191 , 267.25374505, 266.67418786, ..., 266.32231386,\n 267.30821471, 267.57620544],\n [267.67425083, 267.02933005, 266.40183956, ..., 266.40183956,\n 267.33218136, 267.62522813],\n ...,\n [269.75172367, 269.78549485, 269.62317527, ..., 270.06873709,\n 269.95652959, 269.69289643],\n [270.76159117, 270.80080932, 270.75832299, ..., 270.33237024,\n 270.18748095, 269.91186447],\n [271.10692881, 271.19516966, 271.15268333, ..., 270.63848973,\n 270.47290197, 270.30513541]],\n\n [[267.29841017, 267.25483444, 267.06745881, ..., 265.76345515,\n 266.3157775 , 266.53692432],\n [267.55441757, 267.51084184, 267.31801925, ..., 266.01728376,\n 266.99338007, 267.2613708 ],\n [267.77338561, 267.59363573, 267.37684648, ..., 266.09898825,\n 267.00318461, 267.28860563],\n ...,\n [269.32359214, 269.41945874, 269.29091034, ..., 270.08507799,\n 269.90750689, 269.55781167],\n [270.24957636, 270.34871114, 270.35088993, ..., 270.20600063,\n 270.01317803, 269.67110857],\n [270.62105944, 270.76703813, 270.76921692, ..., 270.43695199,\n 270.18857034, 270.01099925]],\n\n ...,\n\n [[271.48168007, 271.36729379, 271.24637114, ..., 270.89776532,\n 270.98164859, 270.96857587],\n [271.81830257, 271.70282689, 271.56447396, ..., 271.43701495,\n 271.53723913, 271.69084357],\n [272.18107051, 271.92179493, 271.77690563, ..., 272.04271757,\n 272.15165689, 272.3107083 ],\n ...,\n [275.28910932, 274.99388376, 274.74441272, ..., 276.07565121,\n 276.18350114, 276.35344648],\n [275.60285456, 275.36536684, 275.34575777, ..., 276.91993095,\n 276.99618847, 277.08551871],\n [275.90788466, 275.95254978, 275.9329407 , ..., 278.0169499 ,\n 277.9058318 , 277.90365301]],\n\n [[269.88462964, 269.78658425, 269.64496313, ..., 269.72231005,\n 269.85957359, 269.92602658],\n [270.1308325 , 270.03278711, 269.93147354, ..., 270.19946427,\n 270.40427019, 270.72237301],\n [270.45656107, 270.21471578, 270.10904464, ..., 270.84329566,\n 271.05463794, 271.37056197],\n ...,\n [273.1440941 , 273.02535024, 272.86738823, ..., 274.12127981,\n 274.27488425, 274.4742432 ],\n [273.5765832 , 273.50795143, 273.58638774, ..., 274.72698243,\n 274.85553083, 275.00150951],\n [273.94697689, 274.12127981, 274.19971612, ..., 275.72704539,\n 275.64207272, 275.67148634]],\n\n [[269.74954488, 269.63951617, 269.51096777, ..., 268.99459539,\n 269.11442864, 269.11224985],\n [269.87046752, 269.76043881, 269.70596915, ..., 269.16345133,\n 269.50443141, 269.90097053],\n [269.85630541, 269.81381908, 269.78222667, ..., 269.61446012,\n 269.94672505, 270.34435357],\n ...,\n [273.29007279, 273.09833959, 273.18440165, ..., 273.11794867,\n 273.21381527, 273.48943175],\n [274.379466 , 274.08641922, 273.44258784, ..., 273.57331502,\n 273.64957255, 273.81298153],\n [273.89904359, 273.55370595, 272.90769578, ..., 274.27815243,\n 274.27488425, 274.25309638]]])" }, "execution_count": 41, "metadata": {}, "output_type": "execute_result" } ], "source": [ "np.asarray(nc_data['t2m'][:])" ], "metadata": { "collapsed": false, "ExecuteTime": { "end_time": "2024-06-11T06:41:37.790393500Z", "start_time": "2024-06-11T06:41:37.756209300Z" } }, "id": "d189f90ec07c8690" }, { "cell_type": "code", "execution_count": 42, "outputs": [ { "data": { "text/plain": "(8784, 13, 31)" }, "execution_count": 42, "metadata": {}, "output_type": "execute_result" } ], "source": [ "np.asarray(nc_data['t2m'][:]).shape" ], "metadata": { "collapsed": false, "ExecuteTime": { "end_time": "2024-06-11T06:41:37.862579700Z", "start_time": "2024-06-11T06:41:37.787379500Z" } }, "id": "6a90a501e4374806" }, { "cell_type": "code", "execution_count": 43, "outputs": [], "source": [ "def find_closest_number_index(arr, target):\n", " arr.sort() # 对数组进行排序\n", " left, right = 0, len(arr) - 1\n", " closest_index = 0\n", "\n", " while left <= right:\n", " mid = left + (right - left) // 2\n", " # 更新最接近数值的索引\n", " if abs(arr[mid] - target) < abs(arr[closest_index] - target):\n", " closest_index = mid\n", " # 根据目标值与中间值的比较，决定搜索左半部分还是右半部分\n", " if arr[mid] < target:\n", " left = mid + 1\n", " elif arr[mid] > target:\n", " right = mid - 1\n", " else:\n", " return mid # 如果找到精确匹配，直接返回索引\n", " return closest_index" ], "metadata": { "collapsed": false, "ExecuteTime": { "end_time": "2024-06-11T06:41:37.870067500Z", "start_time": "2024-06-11T06:41:37.820315500Z" } }, "id": "738d2236e3320758" }, { "cell_type": "code", "execution_count": 44, "outputs": [], "source": [ "target_cols = ['t2m']\n", "times = np.asarray(nc_data['time'][:]).tolist()\n", "times = [start_date + dt.timedelta(hours=x) for x in times]" ], "metadata": { "collapsed": false, "ExecuteTime": { "end_time": "2024-06-11T06:41:37.870067500Z", "start_time": "2024-06-11T06:41:37.834951500Z" } }, "id": "336150c5fe22b4db" }, { "cell_type": "code", "execution_count": 45, "outputs": [], "source": [ "time_index = pd.to_datetime(times * stations.shape[0])\n", "stations['lat'] = stations['lat'].astype(float)\n", "stations['lon'] = stations['lon'].astype(float)\n", "stations_out = stations.copy()" ], "metadata": { "collapsed": false, "ExecuteTime": { "end_time": "2024-06-11T06:41:37.871070500Z", "start_time": "2024-06-11T06:41:37.848726Z" } }, "id": "dfc81e6752e2c51a" }, { "cell_type": "code", "execution_count": 46, "outputs": [ { "data": { "text/plain": " state lon lat lon_index lat_index best_lon best_lat\n0 iowa 93.5 41.1 30 2 -89.0 41.0", "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
statelonlatlon_indexlat_indexbest_lonbest_lat
0iowa93.541.1302-89.041.0
\n
" }, "execution_count": 46, "metadata": {}, "output_type": "execute_result" } ], "source": [ "lon_index = list()\n", "lat_index = list()\n", "best_lons = list()\n", "best_lats = list()\n", "for i in range(stations.shape[0]):\n", " # 获得观测点所在的经纬度\n", " stat_lat = stations.iloc[i]['lat']\n", " stat_lon = stations.iloc[i]['lon']\n", " # 获得观测点所在经纬度对应最近的网格数据的经纬度\n", " best_lat_index = find_closest_number_index(lat, stat_lat)\n", " best_lon_index = find_closest_number_index(lon, stat_lon)\n", " lat_index.append(best_lat_index)\n", " lon_index.append(best_lon_index)\n", " best_lons.append(lon[best_lon_index])\n", " best_lats.append(lat[best_lat_index])\n", "stations_out['lon_index'] = lon_index\n", "stations_out['lat_index'] = lat_index\n", "stations_out['best_lon'] = best_lons\n", "stations_out['best_lat'] = best_lats\n", "stations_out" ], "metadata": { "collapsed": false, "ExecuteTime": { "end_time": "2024-06-11T06:41:37.880042100Z", "start_time": "2024-06-11T06:41:37.866999300Z" } }, "id": "3eccbc89ab82bf16" }, { "cell_type": "code", "execution_count": 47, "outputs": [], "source": [ "for tgt in target_cols:\n", " tmp = np.asarray(nc_data[tgt][:])\n", " stations_out[tgt] = stations_out.apply(lambda x: tmp[:, len(lat) - x['lat_index'] - 1, x['lon_index']].squeeze(),axis=1)" ], "metadata": { "collapsed": false, "ExecuteTime": { "end_time": "2024-06-11T06:41:37.953643400Z", "start_time": "2024-06-11T06:41:37.882051700Z" } }, "id": "eb2d82717535c00b" }, { "cell_type": "code", "execution_count": 48, "outputs": [], "source": [ "result_df = stations_out.explode(column=target_cols).reset_index(drop=True)\n", "result_df['date_time'] = time_index\n", "result_df[['date_time', 't2m']].to_csv('./temper.csv', index=False, encoding='utf-8-sig')" ], "metadata": { "collapsed": false, "ExecuteTime": { "end_time": "2024-06-11T06:41:37.961281200Z", "start_time": "2024-06-11T06:41:37.913630800Z" } }, "id": "f347ca967bfcafce" } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 2 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython2", "version": "2.7.6" } }, "nbformat": 4, "nbformat_minor": 5 }