import streamlit as st import numpy as np import matplotlib.pyplot as plt import seaborn as sns # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ predictions histogram ~~~~~~~~~~~~~~~~~~~~~~~~~~ @st.cache_data def pred_hist(pred): # Creating histogram hist, axs = plt.subplots(1, 1, figsize =(15, 3), tight_layout = True) # Add x, y gridlines axs.grid( color ='grey', linestyle ='-.', linewidth = 0.5, alpha = 0.6) # Remove axes splines for s in ['top', 'bottom', 'left', 'right']: axs.spines[s].set_visible(False) # Remove x, y ticks axs.xaxis.set_ticks_position('none') axs.yaxis.set_ticks_position('none') # Add padding between axes and labels axs.xaxis.set_tick_params(pad = 5) axs.yaxis.set_tick_params(pad = 10) # Creating histogram N, bins, patches = axs.hist(pred, bins = 12) return hist # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ predictions histogram ~~~~~~~~~~~~~~~~~~~~~~~~~~ @st.cache_data def plot_spectra(specdf = None, color = None, cmap =None, xunits = None, yunits = None): # pass import matplotlib.pyplot as plt import numpy as np fig, ax = plt.subplots(figsize = (30,7)) if color is None or cmap is None: specdf.T.plot(legend=False, ax = ax, color = "blue") else: cats = color.unique() for key, value in cmap.items(): ax.plot([], [], color=value, label = str(key)) plt.legend() for key, value in cmap.items(): idx = color.index[color == key].tolist() specdf.loc[idx].T.plot(legend=False, ax = ax, color = value) ax.set_xlabel(xunits, fontsize=30) ax.set_ylabel(yunits, fontsize=30) plt.margins(x = 0) plt.tight_layout() # plt.legend() return fig @st.cache_data def barhplot(metadf, cmap): counts = metadf.groupby(metadf.columns[0]).size() counts = counts.loc[cmap.keys()] fig, ax = plt.subplots(figsize = (10,5)) ax.barh(counts.index, counts.values, color=cmap.values()) plt.gca().invert_yaxis() plt.xlabel('Count') plt.ylabel(str(metadf.columns[0]).capitalize()) return fig # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Cal/val hist ~~~~~~~~~~~~~~~~~~~~~~~~~~ @st.cache_data def hist(y, y_train, y_test, target_name = 'y'): fig, ax = plt.subplots(figsize = (5,2)) sns.histplot(y, color = "#004e9e", kde = True, label = str(target_name), ax = ax, fill = True) sns.histplot(y_train, color = "#2C6B6F", kde = True, label = str(target_name)+" (Cal)", ax = ax, fill = True) sns.histplot(y_test, color = "#d0f7be", kde = True, label = str(target_name)+" (Val)", ax = ax, fill = True) ax.set_xlabel(str(target_name)) plt.legend() plt.tight_layout() return fig @st.cache_data def reg_plot( meas, pred, train_idx, test_idx): a0 = np.ones(2) a1 = np.ones(2) for i in range(len(meas)): meas[i] = np.array(meas[i]).reshape(-1, 1) pred[i] = np.array(pred[i]).reshape(-1, 1) from sklearn.linear_model import LinearRegression M = LinearRegression() M.fit(meas[i], pred[i]) a1[i] = np.round(M.coef_[0][0],2) a0[i] = np.round(M.intercept_[0],2) ec = np.subtract(np.array(meas[0]).reshape(-1), np.array(pred[0]).reshape(-1)) et = np.subtract(np.array(meas[1]).reshape(-1), np.array(pred[1]).reshape(-1)) fig, ax = plt.subplots(figsize = (12,4)) sns.regplot(x = meas[0] , y = pred[0], color="#2C6B6F", label = f'Cal (Predicted = {a0[0]} + {a1[0]} x Measured)', scatter_kws={'edgecolor': 'black'}) sns.regplot(x = meas[1], y = pred[1], color='#d0f7be', label = f'Val (Predicted = {a0[1]} + {a1[1]} x Measured)', scatter_kws={'edgecolor': 'black'}) plt.plot([np.min(meas[0]) - 0.05, np.max([meas[0]]) + 0.05], [np.min(meas[0]) - 0.05, np.max([meas[0]]) + 0.05], color = 'black') for i, txt in enumerate(train_idx): #plt.annotate(txt ,(np.array(meas[0]).reshape(-1)[i],ec[i])) if np.abs(ec[i])> np.mean(ec)+ 3*np.std(ec): plt.annotate(txt ,(np.array(meas[0]).reshape(-1)[i], np.array(pred[0]).reshape(-1)[i])) for i, txt in enumerate(test_idx): if np.abs(et[i])> np.mean(et)+ 3*np.std(et): plt.annotate(txt ,(np.array(meas[1]).reshape(-1)[i], np.array(pred[1]).reshape(-1)[i])) ax.set_ylabel('Predicted values') ax.set_xlabel('Measured values') plt.legend() plt.margins(0) # fig.savefig('./report/figures/measured_vs_predicted.png') return fig # Resid plot @st.cache_data def resid_plot( meas, pred, train_idx, test_idx): a0 = np.ones(2) a1 = np.ones(2) e = [np.subtract(meas[0] ,pred[0]), np.subtract(meas[1], pred[1])] for i in range(len(meas)): from sklearn.linear_model import LinearRegression M = LinearRegression() M.fit( np.array(meas[i]).reshape(-1,1), np.array(e[i]).reshape(-1,1)) a1[i] = np.round(M.coef_[0],2) a0[i] = np.round(M.intercept_,2) fig, ax = plt.subplots(figsize = (12,4)) sns.scatterplot(x = pred[0], y = e[0], color="#2C6B6F", label = f'Cal', edgecolor="black") sns.scatterplot(x = pred[1], y = e[1], color="#d0f7be", label = f'Val', edgecolor="black") # sns.scatterplot(x = pred[0], y = e[0], color='blue', label = f'Cal (Residual = {a0[0]} + {a1[0]} * Predicted)') # sns.scatterplot(x = pred[1], y = e[1], color='green', label = f'Val (Residual = {a0[1]} + {a1[1]} * Predicted)') plt.axhline(y= 0, c ='black', linestyle = ':') lim = np.max(abs(np.concatenate([e[0], e[1]], axis = 0)))*1.1 plt.ylim(- lim, lim ) for i in range(2): e[i] = np.array(e[i]).reshape(-1,1) for i, txt in enumerate(train_idx): #plt.annotate(txt ,(np.array(meas[0]).reshape(-1)[i],ec[i])) if np.abs(e[0][i])> np.mean(e[0])+ 3*np.std(e[0]): plt.annotate(txt ,(np.array(pred[0]).reshape(-1)[i],e[0][i])) for i, txt in enumerate(test_idx): if np.abs(e[1][i])> np.mean(e[1])+ 3*np.std(e[1]): plt.annotate(txt ,(np.array(pred[1]).reshape(-1)[i],e[1][i])) ax.set_xlabel(f'{ train_idx.shape}') ax.set_ylabel('Residuals') ax.set_xlabel('Predicted values') plt.legend() plt.margins(0) # fig.savefig('./report/figures/residuals_plot.png') return fig