#combine the 3 dfs with GCNN RF,SVM,LGBM data
expr_1 = first8
expr_2 = second8
expr_3 = third8
from iter_plot_help_funcs import find_active_percents, plot_metrics, plot_prec_rec_curve, plot_prec_rec_vs_tresh
for exper in [expr_1, expr_2, expr_3]:
exper = find_active_percents(exper, exp)
# plot_metrics(exper,exp)
# plot_prec_rec_curve(exper,exp)
# plot_prec_rec_vs_tresh(exper,exp)
# break
#get gCNN rows:
from iter_plot_help_funcs import find_active_percents, plot_metrics, plot_prec_rec_curve, plot_prec_rec_vs_tresh, plot_avg_percent_found, set_sns_pal
plot_avg_percent_found(pd.concat([expr_1, expr_2, expr_3]),
'Mean Active Recovery for Exp_4', 15, 10)
for exper in [expr_1, expr_2, expr_3]:
exper_gcnn = exper[exper['Classifier'] == 'GCNN_pytorch']
df_list = []
for _, row in exper_gcnn.iterrows():
hist = row['hist']
row_df = pd.DataFrame(hist)
test = pd.melt(row_df.reset_index(),
id_vars=['index'],
value_name='Score',
var_name='Metric')
test['AID'] = row['AID']
test['Iter_num'] = row['Iteration Number']
df_list.append(test)
merged_df = pd.concat(df_list)
g = sns.relplot(x='index',
diverse_run=pickle.load(pickle_off)
pickle_off.close()
expr_1 = random_run[random_run.AID != 'AID_605']
expr_2 = diverse_run[diverse_run.AID != 'AID_605']
'''This section plots the graphs'''
from iter_plot_help_funcs import find_active_percents,plot_metrics,plot_prec_rec_curve,plot_prec_rec_vs_tresh,plot_avg_percent_found,set_sns_pal
set_sns_pal('unpaired')
for exper in [expr_1,expr_2]:
exper = find_active_percents(exper,exp)
plot_metrics(exper,exp)
# plot_prec_rec_curve(exper,exp)
# plot_prec_rec_vs_tresh(exper,exp)
# break
#get gCNN rows:
plot_avg_percent_found(expr_1,'Mean Active Recovery for Classifiers with Diverse Exploration')
plot_avg_percent_found(expr_2,'Mean Active Recovery for Classifiers with Random Exploration \n Initial Selection Strategy',10,5)
'''Check difference between the random and diverse selections'''
from iter_plot_help_funcs import get_checkpointsdf
random_checkpoint = get_checkpointsdf(expr_1,10,5)
class_selection_list=[]
for _,row in random_checkpoint.iterrows():
class_selection_list.append(row.Classifier+'_random')
random_checkpoint['Exp_Cond'] = class_selection_list
diverse_checkpoint = get_checkpointsdf(expr_2,10,5)
class_selection_list=[]
for _,row in diverse_checkpoint.iterrows():
class_selection_list.append(row.Classifier+'_diverse')
diverse_checkpoint['Exp_Cond'] = class_selection_list
merged_23 = pd.concat([random_checkpoint,diverse_checkpoint])
plot_metrics(exper, exp)
# plot_prec_rec_curve(exper,exp)
# plot_prec_rec_vs_tresh(exper,exp)
# break
for exper in [svmexpr_1, svmexpr_2, svmexpr_3]:
exper = find_active_percents(exper, exp)
plot_metrics(exper, exp)
# plot_prec_rec_curve(exper,exp)
# plot_prec_rec_vs_tresh(exper,exp)
# break
from iter_plot_help_funcs import plot_avg_percent_found
merged_df = pd.concat([expr_1, expr_2, expr_3])
svmmerged_df = pd.concat([svmexpr_1, svmexpr_2, svmexpr_3])
plot_avg_percent_found(merged_df)
plot_avg_percent_found(svmmerged_df)
#get gCNN rows:
for exper in [expr_1, expr_2, expr_3]:
exper_gcnn = exper[exper['Classifier'] == 'GCNN_pytorch']
df_list = []
for _, row in exper_gcnn.iterrows():
hist = row['hist']
row_df = pd.DataFrame(hist)
test = pd.melt(row_df.reset_index(),
id_vars=['index'],
value_name='Score',
var_name='Metric')
test['AID'] = row['AID']
test['Iter_num'] = row['Iteration Number']
df_list.append(test)
exp = Experiment(api_key="sqMrI9jc8kzJYobRXRuptF5Tj",
project_name="iter_plotting",
workspace="gdreiman1",
disabled=False)
exp.log_code = True
exp.log_other('Hypothesis',
'''These are my plots from the intial iterations Iter_7 ''')
import pickle
import os
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np
data_dir = '/home/gabriel/Dropbox/UCL/Thesis/Data'
gcnn_initial = 'second_diverse_GCNN_50epoch_iter_run.pkl'
save_path = os.path.join(data_dir, gcnn_initial)
pickle_off = open(save_path, 'rb')
gcnn_initial = pickle.load(pickle_off)
pickle_off.close()
from iter_plot_help_funcs import find_active_percents, plot_metrics, plot_prec_rec_curve, plot_prec_rec_vs_tresh, plot_avg_percent_found, set_sns_pal
set_sns_pal('unpaired')
for exper in [gcnn_initial]:
exper = find_active_percents(exper, exp)
plot_metrics(exper, exp)
plot_avg_percent_found(gcnn_initial,
'Mean Active Recovery for \n Initial GCNN Experiment',
10, 5)
#combine the 3 dfs with GCNN RF,SVM,LGBM data
expr_1 = first8
expr_2 = second8
expr_3 = third8
from iter_plot_help_funcs import find_active_percents, plot_metrics, plot_prec_rec_curve, plot_prec_rec_vs_tresh
for exper in [expr_1, expr_2, expr_3]:
exper = find_active_percents(exper, exp)
# plot_metrics(exper,exp)
# plot_prec_rec_curve(exper,exp)
# plot_prec_rec_vs_tresh(exper,exp)
# break
#get gCNN rows:
from iter_plot_help_funcs import find_active_percents, plot_metrics, plot_prec_rec_curve, plot_prec_rec_vs_tresh, plot_avg_percent_found, set_sns_pal
plot_avg_percent_found(
pd.concat([expr_1, expr_2, expr_3]),
'Mean Active Recovery for Classifiers with \n Epsilon-Greedy Diverse Exploration',
10, 5)
for exper in [expr_1, expr_2, expr_3]:
exper_gcnn = exper[exper['Classifier'] == 'GCNN_pytorch']
df_list = []
for _, row in exper_gcnn.iterrows():
hist = row['hist']
row_df = pd.DataFrame(hist)
test = pd.melt(row_df.reset_index(),
id_vars=['index'],
value_name='Score',
var_name='Metric')
test['AID'] = row['AID']
test['Iter_num'] = row['Iteration Number']
df_list.append(test)
merged_df = pd.concat(df_list)
#combine the 3 dfs with GCNN RF,SVM,LGBM data
expr_1 = first8
expr_2 = second8
expr_3 = third8
from iter_plot_help_funcs import find_active_percents, plot_metrics, plot_prec_rec_curve, plot_prec_rec_vs_tresh
for exper in [expr_1, expr_2, expr_3]:
exper = find_active_percents(exper, exp)
plot_metrics(exper, exp)
# plot_prec_rec_curve(exper,exp)
# plot_prec_rec_vs_tresh(exper,exp)
# break
#get gCNN rows:
from iter_plot_help_funcs import find_active_percents, plot_metrics, plot_prec_rec_curve, plot_prec_rec_vs_tresh, plot_avg_percent_found, set_sns_pal
plot_avg_percent_found(pd.concat([expr_1, expr_2, expr_3]),
'Mean Active Recovery for Test data', 10, 5)
g = sns.relplot(x="Iteration Number",
y="Score",
hue='Classifier',
style="Metric",
col="AID",
col_wrap=3,
data=pd.concat([expr_1, expr_2, expr_3]),
kind='line',
legend='full',
markers=True)
for exper in [expr_1, expr_2, expr_3]:
exper_gcnn = exper[exper['Classifier'] == 'GCNN_pytorch']
df_list = []
for _, row in exper_gcnn.iterrows():
