Skip to content
Snippets Groups Projects
Select Git revision
  • master default
1 result
Blame Permalink
visualize.py 5.33 KiB
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
132
133
134
135
136
137
138
139 






from  packages import * 


# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 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, xunits, yunits):
    fig, ax = plt.subplots(figsize = (30,7))
    if isinstance(specdf.columns[0], str):
        specdf.T.plot(legend=False, ax = ax, color = '#2474b4')
        min = 0
    else: 
        min = np.max(specdf.columns)
        specdf.T.plot(legend=False, ax = ax, color = '#2474b4').invert_xaxis()

    ax.set_xlabel(xunits, fontsize=30)
    ax.set_ylabel(yunits, fontsize=30)
    plt.margins(x = 0)
    plt.tight_layout()
    return fig


# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Cal/val hist ~~~~~~~~~~~~~~~~~~~~~~~~~~
@st.cache_data
def hist(y, y_train, y_test, target_name = 'y'):
    fig, ax = plt.subplots(figsize = (12,3))
    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)

        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)):
        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

Documentation | Mentions légales | CGU | Accessibilité : non conforme