File size: 4,137 Bytes
93196f3 f63fff0 41f86f5 98b5ad2 460d7b4 508da0c 460d7b4 508da0c fb5a6cc 11999c7 98b5ad2 b3348ab 991eed9 c5595b8 460d7b4 dc609e2 b3348ab c5595b8 daa5b98 20fb87c f2e9086 20fb87c 15ddc73 20fb87c 510e15b ad01300 510e15b 20fb87c ad01300 510e15b 98b5ad2 606c1e9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 |
import streamlit as st
from data_utils import *
import xarray as xr
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import pickle
import glob, os
import re
import tensorflow as tf
import netCDF4
import copy
import string
import h5py
from tqdm import tqdm
st.title('A _Quickstart Notebook_ for :blue[ClimSim]:' ),st.link_button("ClimSim", "https://huggingface.co/datasets/LEAP/subsampled_low_res/tree/main")
st.header('**Step 1:** Import data_utils')
st.code('''from data_utils import *''',language='python')
st.header('**Step 2:** Instantiate class')
st.header('**Step 3:** Load training and validation data')
st.header('**Step 4:** Train models')
st.subheader('Train constant prediction model')
st.sidebar.link_button("Go to Original Dataset", "https://huggingface.co/datasets/LEAP/subsampled_low_res/tree/main")
grid_info = xr.open_dataset('ClimSim_low-res_grid-info.nc')
input_mean = xr.open_dataset('input_mean.nc')
input_max = xr.open_dataset('input_max.nc')
input_min = xr.open_dataset('input_min.nc')
output_scale = xr.open_dataset('output_scale.nc')
data = data_utils(grid_info = grid_info,
input_mean = input_mean,
input_max = input_max,
input_min = input_min,
output_scale = output_scale)
data.set_to_v1_vars()
data.input_train = data.load_npy_file('train_input_small.npy')
data.target_train = data.load_npy_file('train_target_small.npy')
data.input_val = data.load_npy_file('val_input_small.npy')
data.target_val = data.load_npy_file('val_target_small.npy')
const_model = data.target_train.mean(axis = 0)
X = data.input_train
bias_vector = np.ones((X.shape[0], 1))
X = np.concatenate((X, bias_vector), axis=1)
mlr_weights = np.linalg.inv(X.transpose()@X)@X.transpose()@data.target_train
data.set_pressure_grid(data_split = 'val')
const_pred_val = np.repeat(const_model[np.newaxis, :], data.target_val.shape[0], axis = 0)
print(const_pred_val.shape)
# Multiple Linear Regression
X_val = data.input_val
bias_vector_val = np.ones((X_val.shape[0], 1))
X_val = np.concatenate((X_val, bias_vector_val), axis=1)
mlr_pred_val = X_val@mlr_weights
print(mlr_pred_val.shape)
# Load your prediction here
# Load predictions into data_utils object
data.model_names = ['const', 'mlr'] # add names of your models here
preds = [const_pred_val, mlr_pred_val] # add your custom predictions here
data.preds_val = dict(zip(data.model_names, preds))
data.reweight_target(data_split = 'val')
data.reweight_preds(data_split = 'val')
data.metrics_names = ['MAE', 'RMSE', 'R2', 'bias']
data.create_metrics_df(data_split = 'val')
letters = string.ascii_lowercase
# create custom dictionary for plotting
dict_var = data.metrics_var_val
plot_df_byvar = {}
for metric in data.metrics_names:
plot_df_byvar[metric] = pd.DataFrame([dict_var[model][metric] for model in data.model_names],
index=data.model_names)
plot_df_byvar[metric] = plot_df_byvar[metric].rename(columns = data.var_short_names).transpose()
# plot figure
fig, axes = plt.subplots(nrows = len(data.metrics_names), sharex = True)
for i in range(len(data.metrics_names)):
plot_df_byvar[data.metrics_names[i]].plot.bar(
legend = False,
ax = axes[i])
if data.metrics_names[i] != 'R2':
axes[i].set_ylabel('$W/m^2$')
else:
axes[i].set_ylim(0,1)
axes[i].set_title(f'({letters[i]}) {data.metrics_names[i]}')
axes[i].set_xlabel('Output variable')
axes[i].set_xticklabels(plot_df_byvar[data.metrics_names[i]].index, \
rotation=0, ha='center')
axes[0].legend(columnspacing = .9,
labelspacing = .3,
handleheight = .07,
handlelength = 1.5,
handletextpad = .2,
borderpad = .2,
ncol = 3,
loc = 'upper right')
fig.set_size_inches(7,8)
fig.tight_layout()
st.pyplot(fig)
# path to target input
data.input_scoring = np.load('score_input_smallnn.npy')
# path to target output
data.target_scoring = np.load('scoring_target_small.npy')
st.markdown('Streamlit p') |