MetapopulationsPython/plotting.py at main · mtomasini/MetapopulationsPython · GitHub

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
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
import matplotlib.pyplot as plt
import pandas as pd

def plot_comparison_set_counts(dataset_1, dataset_2, title, legend_1, legend_2, output_file):
    dataset_1_local = pd.read_csv(f"{dataset_1}_subpop_set_counts.csv", index_col=0)
    dataset_2_local = pd.read_csv(f"{dataset_2}_subpop_set_counts.csv", index_col=0)
    dataset_1_global = pd.read_csv(f"{dataset_1}_metapop_set_counts.csv", index_col=0)
    dataset_2_global = pd.read_csv(f"{dataset_2}_metapop_set_counts.csv", index_col=0)

    plt.plot(dataset_1_local.mean(axis=1), color = 'xkcd:sky blue')
    plt.plot(dataset_1_global.mean(axis=1), color = 'xkcd:blue')
    plt.plot(dataset_2_local.mean(axis=1), color = 'tan')
    plt.plot(dataset_2_global.mean(axis=1), color = 'xkcd:puce')

    plt.fill_between(dataset_1_local.index, dataset_1_local.mean(axis=1) - dataset_1_local.std(axis=1), dataset_1_local.mean(axis=1) + dataset_1_local.std(axis=1), color='xkcd:sky blue', alpha=0.3)
    plt.fill_between(dataset_2_local.index, dataset_2_local.mean(axis=1) - dataset_2_local.std(axis=1), dataset_2_local.mean(axis=1) + dataset_2_local.std(axis=1), color='tan', alpha=0.3)
    plt.fill_between(dataset_1_global.index, dataset_1_global.mean(axis=1) - dataset_1_global.std(axis=1), dataset_1_global.mean(axis=1) + dataset_1_global.std(axis=1), color='xkcd:blue', alpha=0.3)
    plt.fill_between(dataset_2_global.index, dataset_2_global.mean(axis=1) - dataset_2_global.std(axis=1), dataset_2_global.mean(axis=1) + dataset_2_global.std(axis=1), color='xkcd:puce', alpha=0.3)

    plt.axvline(500, color="black", linestyle='--', ymax=1)

    plt.legend([f"{legend_1} subpop avg", f"{legend_1} whole metapop", f"{legend_2} subpop avg", f"{legend_2} whole metapop"])
    plt.ylabel("Number of feature sets")
    plt.xlabel("Generations (x100)")
    plt.grid(linestyle=':', linewidth=0.5)
    plt.title(title)

    plt.savefig(output_file)


def plot_comparison_gini(dataset_1, dataset_2, title, legend_1, legend_2, output_file):
    dataset_1_local = pd.read_csv(f"{dataset_1}_subpop_gini.csv", index_col=0)
    dataset_2_local = pd.read_csv(f"{dataset_2}_subpop_gini.csv", index_col=0)
    dataset_1_global = pd.read_csv(f"{dataset_1}_metapop_gini.csv", index_col=0)
    dataset_2_global = pd.read_csv(f"{dataset_2}_metapop_gini.csv", index_col=0)

    plt.plot(dataset_1_local.mean(axis=1), color = 'xkcd:sky blue')
    plt.plot(dataset_1_global.mean(axis=1), color = 'xkcd:blue')
    plt.plot(dataset_2_local.mean(axis=1), color = 'tan')
    plt.plot(dataset_2_global.mean(axis=1), color = 'xkcd:puce')

    plt.fill_between(dataset_1_local.index, dataset_1_local.mean(axis=1) - dataset_1_local.std(axis=1), dataset_1_local.mean(axis=1) + dataset_1_local.std(axis=1), color='xkcd:sky blue', alpha=0.3)
    plt.fill_between(dataset_2_local.index, dataset_2_local.mean(axis=1) - dataset_2_local.std(axis=1), dataset_2_local.mean(axis=1) + dataset_2_local.std(axis=1), color='tan', alpha=0.3)
    plt.fill_between(dataset_1_global.index, dataset_1_global.mean(axis=1) - dataset_1_global.std(axis=1), dataset_1_global.mean(axis=1) + dataset_1_global.std(axis=1), color='xkcd:blue', alpha=0.3)
    plt.fill_between(dataset_2_global.index, dataset_2_global.mean(axis=1) - dataset_2_global.std(axis=1), dataset_2_global.mean(axis=1) + dataset_2_global.std(axis=1), color='xkcd:puce', alpha=0.3)

    plt.axvline(500, color="black", linestyle='--', ymax=1)

    plt.legend([f"{legend_1} subpop avg", f"{legend_1} whole metapop", f"{legend_2} subpop avg", f"{legend_2} whole metapop"])
    plt.ylabel("Number of feature sets")
    plt.xlabel("Generations (x100)")
    plt.grid(linestyle=':', linewidth=0.5)
    plt.title(title)

    plt.savefig(output_file)


def metapopulation_plot_comparison(dataset_1, dataset_2, title, legend_1, legend_2, output_file, what_measure, number_of_pulses = 5, length_of_pulses = 1, settling_period = 99,  dataset_3 = None, legend_3 = None):
    if what_measure == 'set_counts':
        dataset_1_global = pd.read_csv(f"{dataset_1}_metapop_set_counts.csv", index_col=0)
        dataset_2_global = pd.read_csv(f"{dataset_2}_metapop_set_counts.csv", index_col=0)
    elif what_measure == 'shannon':
        dataset_1_global == pd.read_csv(f"{dataset_1}_metapop_shannon.csv", index_col=0)
        dataset_2_global = pd.read_csv(f"{dataset_2}_metapop_shannon.csv", index_col=0)
    elif what_measure == 'simpson':
        dataset_1_global = pd.read_csv(f"{dataset_1}_metapop_simpson.csv", index_col=0)
        dataset_2_global = pd.read_csv(f"{dataset_2}_metapop_simpson.csv", index_col=0)
    elif what_measure == 'gini':
        dataset_1_global = pd.read_csv(f"{dataset_1}_metapop_gini.csv", index_col=0)
        dataset_2_global = pd.read_csv(f"{dataset_2}_metapop_gini.csv", index_col=0)
    elif what_measure == 'beta':
        dataset_1_global = pd.read_csv(f"{dataset_1}_beta_diversity.csv", index_col=0)
        dataset_2_global = pd.read_csv(f"{dataset_2}_beta_diversity.csv", index_col=0)
    elif what_measure == 'bray-curtis-0-4':
        dataset_1_global = pd.read_csv(f"{dataset_1}_bray-curtis_0-4.csv", index_col=0)
        dataset_2_global = pd.read_csv(f"{dataset_2}_bray-curtis_0-4.csv", index_col=0)
    else:
        raise ValueError("You need to decide what measure you will plot: 'set_counts', 'shannon', 'simpson' or 'gini'?")

    color1 = "xkcd:medium blue"
    color2 = "xkcd:violet"
    color3 = "xkcd:dark orange"

    line1, = plt.plot(dataset_1_global.mean(axis=1), color = color1, label=f"{legend_1}")
    line2, = plt.plot(dataset_2_global.mean(axis=1), color = color2, label=f"{legend_2}")

    plt.fill_between(dataset_1_global.index, dataset_1_global.mean(axis=1) - dataset_1_global.std(axis=1), dataset_1_global.mean(axis=1) + dataset_1_global.std(axis=1), color=color1, alpha=0.2)
    plt.fill_between(dataset_2_global.index, dataset_2_global.mean(axis=1) - dataset_2_global.std(axis=1), dataset_2_global.mean(axis=1) + dataset_2_global.std(axis=1), color=color2, alpha=0.2)

    plt.axvline(500, color="black", linestyle='--', ymax=1)

    if dataset_3 is not None:
        if what_measure == 'set_counts':
            dataset_3_global = pd.read_csv(f"{dataset_3}_metapop_set_counts.csv", index_col=0)
        elif what_measure == 'shannon':
            dataset_3_global == pd.read_csv(f"{dataset_3}_metapop_shannon.csv", index_col=0)
        elif what_measure == 'simpson':
            dataset_3_global = pd.read_csv(f"{dataset_3}_metapop_simpson.csv", index_col=0)
        elif what_measure == 'gini':
            dataset_3_global = pd.read_csv(f"{dataset_3}_metapop_gini.csv", index_col=0)
        elif what_measure == 'beta':
            dataset_3_global = pd.read_csv(f"{dataset_3}_beta_diversity.csv", index_col=0)
        else:
            print("You need to decide what measure you will plot: 'set_counts', 'shannon', 'simpson' or 'gini'?")

        line3, = plt.plot(dataset_3_global.mean(axis=1), color = color3, label=f"{legend_3}")
        plt.fill_between(dataset_3_global.index, dataset_3_global.mean(axis=1) - dataset_3_global.std(axis=1), dataset_3_global.mean(axis=1) + dataset_3_global.std(axis=1), color=color3, alpha=0.2)

    if dataset_3 is not None:
        plt.legend(loc=3, handles=[line1, line2, line3])
    else:
        plt.legend([f"{legend_1}", f"{legend_2}"])

    plt.axvline(500, color="black", linestyle='--', ymax=1)
    for i in range(1, number_of_pulses + 1):
        plt.axvline(500 + i*(length_of_pulses + settling_period), color="dimgrey", linestyle='--', ymax=1)

    match what_measure:
        case 'set_counts':
            plt.ylabel("Number of sets of features")
        case 'shannon':
            plt.ylabel("Shannon diversity")
        case 'simpson':
            plt.ylabel("Simpson diversity")
        case 'gini':
            plt.ylabel(r"Gini-Simpson diversity")
        case 'beta':
            plt.ylabel(r"Whittaker $\beta$-diversity")
    plt.xlabel("Steps (x100)")
    plt.grid(linestyle=':', linewidth=0.5)
    plt.title(title)

    plt.savefig(output_file)


def subpopulation_plot_comparison(dataset_1, dataset_2, title, legend_1, legend_2, output_file, what_measure, number_of_pulses = 5, length_of_pulses = 1, settling_period = 99,  dataset_3 = None, legend_3 = None):
    if what_measure == 'set_counts':
        dataset_1_global = pd.read_csv(f"{dataset_1}_subpop_set_counts.csv", index_col=0)
        dataset_2_global = pd.read_csv(f"{dataset_2}_subpop_set_counts.csv", index_col=0)
    elif what_measure == 'shannon':
        dataset_1_global == pd.read_csv(f"{dataset_1}_subpop_shannon.csv", index_col=0)
        dataset_2_global = pd.read_csv(f"{dataset_2}_subpop_shannon.csv", index_col=0)
    elif what_measure == 'simpson':
        dataset_1_global = pd.read_csv(f"{dataset_1}_subpop_simpson.csv", index_col=0)
        dataset_2_global = pd.read_csv(f"{dataset_2}_subpop_simpson.csv", index_col=0)
    elif what_measure == 'gini':
        dataset_1_global = pd.read_csv(f"{dataset_1}_subpop_gini.csv", index_col=0)
        dataset_2_global = pd.read_csv(f"{dataset_2}_subpop_gini.csv", index_col=0)
    else:
        raise ValueError("You need to decide what measure you will plot: 'set_counts', 'shannon', 'simpson' or 'gini'?")

    color1 = "xkcd:medium blue"
    color2 = "xkcd:violet"
    color3 = "xkcd:dark orange"

    line1, = plt.plot(dataset_1_global.mean(axis=1), color = color1, label=f"{legend_1}")
    line2, = plt.plot(dataset_2_global.mean(axis=1), color = color2, label=f"{legend_2}")

    plt.fill_between(dataset_1_global.index, dataset_1_global.mean(axis=1) - dataset_1_global.std(axis=1), dataset_1_global.mean(axis=1) + dataset_1_global.std(axis=1), color=color1, alpha=0.2)
    plt.fill_between(dataset_2_global.index, dataset_2_global.mean(axis=1) - dataset_2_global.std(axis=1), dataset_2_global.mean(axis=1) + dataset_2_global.std(axis=1), color=color2, alpha=0.2)

    plt.axvline(500, color="black", linestyle='--', ymax=1)

    if dataset_3 is not None:
        if what_measure == 'set_counts':
            dataset_3_global = pd.read_csv(f"{dataset_3}_subpop_set_counts.csv", index_col=0)
        elif what_measure == 'shannon':
            dataset_3_global == pd.read_csv(f"{dataset_3}_subpop_shannon.csv", index_col=0)
        elif what_measure == 'simpson':
            dataset_3_global = pd.read_csv(f"{dataset_3}_subpop_simpson.csv", index_col=0)
        elif what_measure == 'gini':
            dataset_3_global = pd.read_csv(f"{dataset_3}_subpop_gini.csv", index_col=0)
        else:
            print("You need to decide what measure you will plot: 'set_counts', 'shannon', 'simpson' or 'gini'?")

        line3, = plt.plot(dataset_3_global.mean(axis=1), color = color3, label=f"{legend_3}")
        plt.fill_between(dataset_3_global.index, dataset_3_global.mean(axis=1) - dataset_3_global.std(axis=1), dataset_3_global.mean(axis=1) + dataset_3_global.std(axis=1), color=color3, alpha=0.2)

    if dataset_3 is not None:
        plt.legend(loc=3, handles=[line1, line2, line3])
    else:
        plt.legend([f"{legend_1}", f"{legend_2}"])

    plt.axvline(500, color="black", linestyle='--', ymax=1)
    for i in range(1, number_of_pulses + 1):
        plt.axvline(500 + i*(length_of_pulses + settling_period), color="dimgrey", linestyle='--', ymax=1)

    match what_measure:
        case 'set_counts':
            plt.ylabel("Number of sets of features")
        case 'shannon':
            plt.ylabel("Shannon diversity")
        case 'simpson':
            plt.ylabel("Simpson diversity")
        case 'gini':
            plt.ylabel("Gini-Simpson diversity")
    # plt.ylim([0, 100])
    plt.xlabel("Steps (x100)")
    plt.grid(linestyle=':', linewidth=0.5)
    plt.title(title)

    plt.savefig(output_file)


def plot_comparison_gini_pulses(dataset_1, dataset_2, title, legend_1, legend_2, number_of_pulses, length_of_pulses, settling_period, output_file, dataset_3=None, legend_3=None):
    dataset_1_local = pd.read_csv(f"{dataset_1}_subpop_gini.csv", index_col=0)
    dataset_2_local = pd.read_csv(f"{dataset_2}_subpop_gini.csv", index_col=0)

    line1, = plt.plot(dataset_1_local.mean(axis=1), color = 'xkcd:sky blue', label=f"{legend_1} subpop avg")
    line2, = plt.plot(dataset_2_local.mean(axis=1), color = 'tan', label=f"{legend_2} subpop avg")
    plt.fill_between(dataset_1_local.index, dataset_1_local.mean(axis=1) - dataset_1_local.std(axis=1), dataset_1_local.mean(axis=1) + dataset_1_local.std(axis=1), color='xkcd:sky blue', alpha=0.3)
    plt.fill_between(dataset_2_local.index, dataset_2_local.mean(axis=1) - dataset_2_local.std(axis=1), dataset_2_local.mean(axis=1) + dataset_2_local.std(axis=1), color='tan', alpha=0.3)

    if dataset_3 is not None:
        dataset_3_local = pd.read_csv(f"{dataset_3}_subpop_gini.csv", index_col=0)
        line3, = plt.plot(dataset_3_local.mean(axis=1), color = 'mediumpurple', label=f"{legend_3} subpop avg")
        plt.fill_between(dataset_3_local.index, dataset_3_local.mean(axis=1) - dataset_3_local.std(axis=1), dataset_3_local.mean(axis=1) + dataset_3_local.std(axis=1), color='mediumpurple', alpha=0.3)
        #plt.legend([f"{legend_1} subpop avg", f"{legend_2} subpop avg", f"{legend_3} subpop avg"])
        plt.legend(loc=3, handles=[line1, line2, line3])

    else:
        plt.legend([f"{legend_1} subpop avg", f"{legend_2} subpop avg"])


    plt.axvline(500, color="black", linestyle='--', ymax=1)
    for i in range(1, number_of_pulses + 1):
        plt.axvline(500 + i*(length_of_pulses + settling_period), color="dimgrey", linestyle='--', ymax=1)


    plt.ylabel("Gini-Simpson diversity index")
    plt.xlabel("Generations (x100)")
    plt.grid(linestyle=':', linewidth=0.5)
    plt.title(title)

    plt.savefig(output_file)


def plot_subpopulation_mean(dataset, subpop_id, output_file, number_of_pulses = 5, length_of_pulses = 1, settling_period = 99):
    # deme = pd.Series(dataset[dataset["Replicate"] == 0][f"{subpop_id}"])
    for replicate in dataset["Replicate"].unique():
        if replicate == 0:
            deme = pd.Series(dataset[dataset["Replicate"] == replicate][f"{subpop_id}"])

        deme = pd.concat([deme, pd.Series(dataset[dataset["Replicate"] == replicate][f"{subpop_id}"])], axis=1)

    fig = plt.plot(deme.mean(axis=1), color="tab:orange")
    std_plus = deme.mean(axis=1) + deme.std(axis=1)
    std_minus = deme.mean(axis=1) - deme.std(axis=1)
    # std_plus cannot be larger than 100 in the beginning (but values can as it can be below 0 and this is a symetric +/-!)
    std_plus[std_plus > 100] = 100
    std_minus[std_minus < 0] = 0
    plt.fill_between(deme.index, std_minus, std_plus, alpha = 0.3, color="tab:orange")
    plt.ylabel("Individuals with extra trait")
    plt.xlabel("Generations (x100)")
    plt.ylim([0, 100])
    plt.grid(linestyle=':', linewidth=0.5)
    plt.title(f"Extra trait in subpopulation {subpop_id}")

    plt.axvline(500, color="black", linestyle='--', ymax=1)
    for i in range(1, number_of_pulses + 1):
        plt.axvline(500 + i*(length_of_pulses + settling_period), color="dimgrey", linestyle='--', ymax=1)

    plt.savefig(output_file)

    return fig, deme