Update app.py

app.py

@@ -19,16 +19,23 @@ st.title('A _Quickstart Notebook_ for :blue[ClimSim]:')
 st.link_button("ClimSim", "https://huggingface.co/datasets/LEAP/subsampled_low_res/tree/main",use_container_width=True)
 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.link_button("Go to Original Dataset", "https://huggingface.co/datasets/LEAP/subsampled_low_res/tree/main",,use_container_width=True)
-
 
+st.header('**Step 2:**  Instantiate class')
+st.code('''#Change the path to your own
+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()''',language='python')
 
+#Change the path to your own
 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')
@@ -43,19 +50,74 @@ data = data_utils(grid_info = grid_info,
 
 data.set_to_v1_vars()
 
+
+st.header('**Step 3:**  Load training and validation data')
+st.code('''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')''',language='python')
+
 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')
 
 
+st.header('**Step 4:**  Train models')
+st.subheader('Train constant prediction model')
+st.code('''const_model = data.target_train.mean(axis = 0)''',language='python')
+
 const_model = data.target_train.mean(axis = 0)
+
+
+st.subheader('Train multiple linear regression model')
+st.text('adding bias unit')
+st.code('''X = data.input_train
+bias_vector = np.ones((X.shape[0], 1))
+X = np.concatenate((X, bias_vector), axis=1)''',language='python')
+
 X = data.input_train
 bias_vector = np.ones((X.shape[0], 1))
 X = np.concatenate((X, bias_vector), axis=1)
+
+
+st.text('create model')
+st.code('''mlr_weights = np.linalg.inv(X.transpose()@X)@X.transpose()@data.target_train''',language='python')
+
 mlr_weights = np.linalg.inv(X.transpose()@X)@X.transpose()@data.target_train
+
+
+st.subheader('Train your models here')
+st.code('''### 
+# train your model here
+###''',language='python')
+
+### 
+# train your model here
+###
+
+
+st.link_button("Go to Original Dataset", "https://huggingface.co/datasets/LEAP/subsampled_low_res/tree/main",use_container_width=True)
+
+st.header('**Step 5:**  Evaluate on validation data')
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
 data.set_pressure_grid(data_split = 'val')
 
+# Constant Prediction
 const_pred_val = np.repeat(const_model[np.newaxis, :], data.target_val.shape[0], axis = 0)
 print(const_pred_val.shape)
 
@@ -63,6 +125,7 @@ print(const_pred_val.shape)
 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)
 
@@ -73,13 +136,11 @@ 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