diff --git a/divis/genetic_groups.py b/divis/genetic_groups.py
deleted file mode 100644
index 6691db1607b0c164b435175c40e9d1c782f79eb7..0000000000000000000000000000000000000000
--- a/divis/genetic_groups.py
+++ /dev/null
@@ -1,114 +0,0 @@
-# Data analysis and manipulation library
-import pandas as pd
-import plotly.express as px
-import os
-
-# System library to manipulate the file system
-from os import path
-from scripts.utils import write_excel
-import shutil
-from tqdm import tqdm
-from scripts.quads import *
-
-df = pd.ExcelFile('data/semantic_cluster_coordinates6.xlsx')
-df1 = pd.read_excel('data/input_data_file.xlsx')
-df2 = pd.read_excel(df)
-#quantitatives variables
-quantitative =['Name (original)','Number of flowers per inflorescence']
-#qualitatives variables
-qualitative = ['Name (original)',
- 'Breeding period',
- 'Geographic origin',
- 'Horticultural group',
- 'Ploidy',
- 'Bush height',
- 'Shape',
- 'Quantity of prickles',
- 'Perfume intensity',
- 'Repeat flowering',
- 'Quantity of bristles by branch',
- 'Shine of upper face',
- 'Corolla form',
- 'Corolla size',
- 'Color repartition',
- 'Duplicature',
- 'Petal color']
-
-df_clus = df1[['Name (original)','Genetic group']]
-df_clus = df_clus.fillna(0)
-df_clus["Genetic group"]= df_clus["Genetic group"].astype(int)
-df_quali = df1[qualitative]
-df_quanti = df1[quantitative]
-
-#make the dataframe that contain only the qualitatives variables
-dataframe_quali = df_quali.merge(df_clus)
-dataframe_quali = dataframe_quali.fillna("missing values")
-
-#make the dataframe that contain only the quantitatives variables
-dataframe_quanti = df_quanti.merge(df_clus)
-dataframe_quanti = dataframe_quanti.rename(columns = {'Number of flowers per inflorescence' : 'Number_of_flowers_per_inflorescence'})
-#make the qualitative analysis
-sdqualitative = sdquali(dataframe_quali, qualitative, 'Genetic group', 0.05)
-sdqualitative=sdqualitative.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
-quali_a = quali_analysis(dataframe_quali, qualitative, 'Genetic group')
-cm = clamod(quali_a,'Genetic group')
-mc = modcla(quali_a,'Genetic group')
-g = globa(quali_a)
-pv = pvalue(quali_a,'Genetic group')
-test_value = vtest(quali_a,'Genetic group',0.05)
-test_value=test_value.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
-w = variable_weight(quali_a)
-w=w.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
-
-#make the quantitative analysis for each quantitative variable
-sd = sdquanti(dataframe_quanti,'Number_of_flowers_per_inflorescence', 'Genetic group')
-sd = sd.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
-quanti_a = quanti_analysis(sd, dataframe_quanti,'Number_of_flowers_per_inflorescence', 'Genetic group',0.05,0.05)
-quanti_a = quanti_a.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
-
-#out :
-#create the new path for the result
-if not os.path.exists('results/Genetic groups') :
- os.makedirs('results/Genetic groups')
-path = 'results/Genetic groups/'
-
-#name the files
-file_name_x2 = 'x2_GG.xlsx'
-file_name_qualitative = 'qualitative_analysis_GG.xlsx'
-file_name_weight = 'weight_GG.xlsx'
-file_name_anova = 'anova_GG.xlsx'
-file_name_quantitative = 'quantitative_analysis_GG.xlsx'
-
-#create the excel files
-write_excel(file_name_x2,'sheet', sdqualitative, idx=True)
-write_excel(file_name_qualitative,'sheet',test_value,idx=True)
-write_excel(file_name_weight,'sheet', w,idx=True)
-write_excel(file_name_anova,'sheet', sd,idx=True)
-write_excel(file_name_quantitative,'sheet', quanti_a, idx=True)
-
-#make the visualisations
-data = pd.ExcelFile(file_name_qualitative)
-col = {'overrepresented' : 'red', 'underrepresented' : 'blue', 'Not significant': 'grey'}
-title = 'Proportions of modalities in each genetic group with Semantic distance'
-df = pd.read_excel(data)
-legend=''
-for i in range (len(df)):
- if legend == '' :
- pass
- else :
- legend = legend+' ; '
- if df['variables'][i] =='Genetic group' :
- legend= legend+ str(df['Genetic group'][i])+' : '+str(round(df['global'][i],2))+'%'
-sunburst = px.sunburst(df, path=['Genetic group', 'variables', 'modalities'],values='mod/cla',title=title, color = 'signification',color_discrete_map=col)
-sunburst.add_annotation(x=0,y=1.1,text=legend,font = dict(color='black',size=14),showarrow=False)
-sunburst.add_annotation(x=0.2,y=1,text= 'Overrepresented',font = dict(color='red',size=14),showarrow=False)
-sunburst.add_annotation(x=0.2,y=0.95,text= 'Underrepresented',font = dict(color='blue',size=14),showarrow=False)
-sunburst.add_annotation(x=0.2,y=0.9,text= 'Not significant',font = dict(color='grey',size=14),showarrow=False)
-sunburst.show()
-
-#move the files in the good directory
-shutil.move(file_name_x2,path+file_name_x2)
-shutil.move(file_name_qualitative,path+file_name_qualitative)
-shutil.move(file_name_weight,path+file_name_weight)
-shutil.move(file_name_anova,path+file_name_anova)
-shutil.move(file_name_quantitative,path+file_name_quantitative)
diff --git a/divis/gower5.py b/divis/gower5.py
deleted file mode 100644
index c061ba63d9cf6214609b35ef700c430a006286fc..0000000000000000000000000000000000000000
--- a/divis/gower5.py
+++ /dev/null
@@ -1,124 +0,0 @@
-# Data analysis and manipulation library
-import pandas as pd
-import plotly.express as px
-import os
-
-# System library to manipulate the file system
-from os import path
-from scripts.utils import write_excel
-import shutil
-from tqdm import tqdm
-from scripts.quads import *
-
-df = pd.ExcelFile('data/gower_cluster_coordinates5.xlsx')
-sheets = df.sheet_names
-df1 = pd.read_excel('data/input_data_file.xlsx')
-for sheet in tqdm(sheets) :
- df2 = pd.read_excel(df, sheet)
- #quantitatives variables
- quantitative =['Name (original)','Number of flowers per inflorescence']
- #qualitatives variables
- qualitative = ['Name (original)',
- 'Breeding period',
- 'Geographic origin',
- 'Horticultural group',
- 'Ploidy',
- 'Bush height',
- 'Shape',
- 'Quantity of prickles',
- 'Perfume intensity',
- 'Repeat flowering',
- 'Quantity of bristles by branch',
- 'Shine of upper face',
- 'Corolla form',
- 'Corolla size',
- 'Color repartition',
- 'Duplicature',
- 'Petal color']
-
- df_quali = df1[qualitative]
- df_quanti = df1[quantitative]
-
- #take the variable cluster from the second table
- #with a merge from df1 to df2
- #merge : df1 = Name(original) ; df2 = Unnamed: 0
- #rename the df2 columns from Unnamed: 0 to Name(original) to make the merge
- df2.rename(columns={'Unnamed: 0' : 'Name (original)'}, inplace = True)
- columns_df2 = ['Name (original)','cluster']
- df2 = df2[columns_df2]
-
- #make the dataframe that contain only the qualitatives variables
- dataframe_quali = df_quali.merge(df2)
- dataframe_quali = dataframe_quali.fillna('missing values')
-
- #make the dataframe that contain only the quantitatives variables
- dataframe_quanti = df_quanti.merge(df2)
- dataframe_quanti = dataframe_quanti.rename(columns = {'Number of flowers per inflorescence' : 'Number_of_flowers_per_inflorescence'})
-
- #make the qualitative analysis
- sdqualitative = sdquali(dataframe_quali, qualitative, 'cluster', 0.05)
- sdqualitative=sdqualitative.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
- quali_a = quali_analysis(dataframe_quali, qualitative, 'cluster')
- cm = clamod(quali_a,'cluster')
- mc = modcla(quali_a,'cluster')
- g = globa(quali_a)
- pv = pvalue(quali_a,'cluster')
- test_value = vtest(quali_a,'cluster',0.05)
- test_value=test_value.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
- w = variable_weight(quali_a)
- w=w.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
-
- #make the quantitative analysis for each quantitative variable
- sd = sdquanti(dataframe_quanti,'Number_of_flowers_per_inflorescence', 'cluster')
- sd = sd.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
- quanti_a = quanti_analysis(sd, dataframe_quanti,'Number_of_flowers_per_inflorescence', 'cluster',0.05,0.05)
- quanti_a = quanti_a.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
-
- #out :
- #create the new path for the result
- if not os.path.exists('results/gower/cluster5') :
- os.makedirs('results/gower/cluster5')
- path = 'results/gower/cluster5/'
-
- #name the files
- file_name_x2 = 'x2_gower_cluster5.xlsx'
- file_name_qualitative = 'qualitative_analysis_gower_cluster5.xlsx'
- file_name_weight = 'weight_gower_cluster5.xlsx'
- file_name_anova = 'anova_gower_cluster5.xlsx'
- file_name_quantitative = 'quantitative_analysis_gower_cluster5.xlsx'
-
- #create the excel files
- write_excel(file_name_x2, sheet, sdqualitative, idx=True)
- write_excel(file_name_qualitative, sheet, test_value,idx=True)
- write_excel(file_name_weight, sheet, w,idx=True)
- write_excel(file_name_anova, sheet, sd,idx=True)
- write_excel(file_name_quantitative, sheet, quanti_a, idx=True)
-
-#make the visualisations
-data = pd.ExcelFile(file_name_qualitative)
-sheets = data.sheet_names
-col = {'overrepresented' : 'red', 'underrepresented' : 'blue', 'Not significant': 'grey'}
-for sheet in sheets :
- title = 'Proportions of modalities in each clusters with Gower distance and '+sheet+' method'
- df = pd.read_excel(data, sheet)
- legend=''
- for i in range (len(df)):
- if legend == '' :
- pass
- else :
- legend = legend+' ; '
- if df['variables'][i] =='cluster' :
- legend= legend+ str(df['cluster'][i])+' : '+str(round(df['global'][i],2))+'%'
- sunburst = px.sunburst(df, path=['cluster', 'variables', 'modalities'],values='mod/cla',title=title, color = 'signification',color_discrete_map=col)
- sunburst.add_annotation(x=0,y=1.1,text=legend,font = dict(color='black',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=1,text= 'Overrepresented',font = dict(color='red',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.95,text= 'Underrepresented',font = dict(color='blue',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.9,text= 'Not significant',font = dict(color='grey',size=14),showarrow=False)
- sunburst.show()
-
-#move the files in the good directory
-shutil.move(file_name_x2,path+file_name_x2)
-shutil.move(file_name_qualitative,path+file_name_qualitative)
-shutil.move(file_name_weight,path+file_name_weight)
-shutil.move(file_name_anova,path+file_name_anova)
-shutil.move(file_name_quantitative,path+file_name_quantitative)
diff --git a/divis/gower6.py b/divis/gower6.py
deleted file mode 100644
index 4b647a47d84c1b93d29541dafea0b5a3b044218c..0000000000000000000000000000000000000000
--- a/divis/gower6.py
+++ /dev/null
@@ -1,127 +0,0 @@
-# Data analysis and manipulation library
-import pandas as pd
-import plotly.express as px
-import os
-
-# System library to manipulate the file system
-from os import path
-from scripts.utils import write_excel
-import shutil
-from tqdm import tqdm
-from scripts.quads import *
-
-df = pd.ExcelFile('data/gower_cluster_coordinates6.xlsx')
-sheets = df.sheet_names
-df1 = pd.read_excel('data/input_data_file.xlsx')
-for sheet in tqdm(sheets) :
- df2 = pd.read_excel(df, sheet)
- #quantitatives variables
- quantitative =['Name (original)','Number of flowers per inflorescence']
- #qualitatives variables
- qualitative = ['Name (original)',
- 'Breeding period',
- 'Geographic origin',
- 'Horticultural group',
- 'Ploidy',
- 'Bush height',
- 'Shape',
- 'Quantity of prickles',
- 'Perfume intensity',
- 'Repeat flowering',
- 'Quantity of bristles by branch',
- 'Shine of upper face',
- 'Corolla form',
- 'Corolla size',
- 'Color repartition',
- 'Duplicature',
- 'Petal color']
-
- df_quali = df1[qualitative]
- df_quanti = df1[quantitative]
-
- #take the variable cluster from the second table
- #with a merge from df1 to df2
- #merge : df1 = Name(original) ; df2 = Unnamed: 0
- #rename the df2 columns from Unnamed: 0 to Name(original) to make the merge
- df2.rename(columns={'Unnamed: 0' : 'Name (original)'}, inplace = True)
- columns_df2 = ['Name (original)','cluster']
- df2 = df2[columns_df2]
-
- #make the dataframe that contain only the qualitatives variables
- dataframe_quali = df_quali.merge(df2)
- dataframe_quali = dataframe_quali.fillna('missing values')
-
- #make the dataframe that contain only the quantitatives variables
- dataframe_quanti = df_quanti.merge(df2)
- dataframe_quanti = dataframe_quanti.rename(columns = {'Number of flowers per inflorescence' : 'Number_of_flowers_per_inflorescence'})
-
- #make the qualitative analysis
- sdqualitative = sdquali(dataframe_quali, qualitative, 'cluster', 0.05)
- sdqualitative=sdqualitative.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
- quali_a = quali_analysis(dataframe_quali, qualitative, 'cluster')
- cm = clamod(quali_a,'cluster')
- mc = modcla(quali_a,'cluster')
- g = globa(quali_a)
- pv = pvalue(quali_a,'cluster')
- test_value = vtest(quali_a,'cluster',0.05)
- test_value=test_value.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
- w = variable_weight(quali_a)
- w=w.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
-
- #make the quantitative analysis for each quantitative variable
- sd = sdquanti(dataframe_quanti,'Number_of_flowers_per_inflorescence', 'cluster')
- sd = sd.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
- quanti_a = quanti_analysis(sd, dataframe_quanti,'Number_of_flowers_per_inflorescence', 'cluster',0.05,0.05)
- quanti_a = quanti_a.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
-
- #out :
- #create the new path for the result
- if not os.path.exists('results/gower/cluster6') :
- os.makedirs('results/gower/cluster6')
- path = 'results/gower/cluster6/'
-
- #name the files
- file_name_x2 = 'x2_gower_cluster6.xlsx'
- file_name_qualitative = 'qualitative_analysis_gower_cluster6.xlsx'
- file_name_weight = 'weight_gower_cluster6.xlsx'
- file_name_anova = 'anova_gower_cluster6.xlsx'
- file_name_quantitative = 'quantitative_analysis_gower_cluster6.xlsx'
-
- #create the excel files
- write_excel(file_name_x2, sheet, sdqualitative, idx=True)
- write_excel(file_name_qualitative, sheet, test_value,idx=True)
- write_excel(file_name_weight, sheet, w,idx=True)
- write_excel(file_name_anova, sheet, sd,idx=True)
- write_excel(file_name_quantitative, sheet, quanti_a, idx=True)
-
-#make the visualisations
-data = pd.ExcelFile(file_name_qualitative)
-sheets = data.sheet_names
-col = {'overrepresented' : 'red', 'underrepresented' : 'blue', 'Not significant': 'grey'}
-for sheet in sheets :
- title = 'Proportions of modalities in each clusters with Gower distance and '+sheet+' method'
- df = pd.read_excel(data, sheet)
- legend=''
- for i in range (len(df)):
- if legend == '' :
- pass
- else :
- legend = legend+' ; '
- if df['variables'][i] =='cluster' :
- legend= legend+ str(df['cluster'][i])+' : '+str(round(df['global'][i],2))+'%'
- sunburst = px.sunburst(df, path=['cluster', 'variables', 'modalities'],values='mod/cla',title=title, color = 'signification',color_discrete_map=col)
- sunburst.add_annotation(x=0,y=1.1,text=legend,font = dict(color='black',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=1,text= 'Overrepresented',font = dict(color='red',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.95,text= 'Underrepresented',font = dict(color='blue',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.9,text= 'Not significant',font = dict(color='grey',size=14),showarrow=False)
- sunburst.show()
-
-#move the files in the good directory
-shutil.move(file_name_x2,path+file_name_x2)
-shutil.move(file_name_qualitative,path+file_name_qualitative)
-shutil.move(file_name_weight,path+file_name_weight)
-shutil.move(file_name_anova,path+file_name_anova)
-shutil.move(file_name_quantitative,path+file_name_quantitative)
-
-
-
diff --git a/divis/gower7.py b/divis/gower7.py
deleted file mode 100644
index 4e2d5f7c37471668d554047aade836be33d3770e..0000000000000000000000000000000000000000
--- a/divis/gower7.py
+++ /dev/null
@@ -1,124 +0,0 @@
-# Data analysis and manipulation library
-import pandas as pd
-import plotly.express as px
-import os
-
-# System library to manipulate the file system
-from os import path
-from scripts.utils import write_excel
-import shutil
-from tqdm import tqdm
-from scripts.quads import *
-
-df = pd.ExcelFile('data/gower_cluster_coordinates7.xlsx')
-sheets = df.sheet_names
-df1 = pd.read_excel('data/input_data_file.xlsx')
-for sheet in tqdm(sheets) :
- df2 = pd.read_excel(df, sheet)
- #quantitatives variables
- quantitative =['Name (original)','Number of flowers per inflorescence']
- #qualitatives variables
- qualitative = ['Name (original)',
- 'Breeding period',
- 'Geographic origin',
- 'Horticultural group',
- 'Ploidy',
- 'Bush height',
- 'Shape',
- 'Quantity of prickles',
- 'Perfume intensity',
- 'Repeat flowering',
- 'Quantity of bristles by branch',
- 'Shine of upper face',
- 'Corolla form',
- 'Corolla size',
- 'Color repartition',
- 'Duplicature',
- 'Petal color']
-
- df_quali = df1[qualitative]
- df_quanti = df1[quantitative]
-
- #take the variable cluster from the second table
- #with a merge from df1 to df2
- #merge : df1 = Name(original) ; df2 = Unnamed: 0
- #rename the df2 columns from Unnamed: 0 to Name(original) to make the merge
- df2.rename(columns={'Unnamed: 0' : 'Name (original)'}, inplace = True)
- columns_df2 = ['Name (original)','cluster']
- df2 = df2[columns_df2]
-
- #make the dataframe that contain only the qualitatives variables
- dataframe_quali = df_quali.merge(df2)
- dataframe_quali = dataframe_quali.fillna('missing values')
-
- #make the dataframe that contain only the quantitatives variables
- dataframe_quanti = df_quanti.merge(df2)
- dataframe_quanti = dataframe_quanti.rename(columns = {'Number of flowers per inflorescence' : 'Number_of_flowers_per_inflorescence'})
-
- #make the qualitative analysis
- sdqualitative = sdquali(dataframe_quali, qualitative, 'cluster', 0.05)
- sdqualitative=sdqualitative.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
- quali_a = quali_analysis(dataframe_quali, qualitative, 'cluster')
- cm = clamod(quali_a,'cluster')
- mc = modcla(quali_a,'cluster')
- g = globa(quali_a)
- pv = pvalue(quali_a,'cluster')
- test_value = vtest(quali_a,'cluster',0.05)
- test_value=test_value.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
- w = variable_weight(quali_a)
- w=w.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
-
- #make the quantitative analysis for each quantitative variable
- sd = sdquanti(dataframe_quanti,'Number_of_flowers_per_inflorescence', 'cluster')
- sd = sd.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
- quanti_a = quanti_analysis(sd, dataframe_quanti,'Number_of_flowers_per_inflorescence', 'cluster',0.05,0.05)
- quanti_a = quanti_a.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
-
- #out :
- #create the new path for the result
- if not os.path.exists('results/gower/cluster7') :
- os.makedirs('results/gower/cluster7')
- path = 'results/gower/cluster7/'
-
- #name the files
- file_name_x2 = 'x2_gower_cluster7.xlsx'
- file_name_qualitative = 'qualitative_analysis_gower_cluster7.xlsx'
- file_name_weight = 'weight_gower_cluster7.xlsx'
- file_name_anova = 'anova_gower_cluster7.xlsx'
- file_name_quantitative = 'quantitative_analysis_gower_cluster7.xlsx'
-
- #create the excel files
- write_excel(file_name_x2, sheet, sdqualitative, idx=True)
- write_excel(file_name_qualitative, sheet, test_value,idx=True)
- write_excel(file_name_weight, sheet, w,idx=True)
- write_excel(file_name_anova, sheet, sd,idx=True)
- write_excel(file_name_quantitative, sheet, quanti_a, idx=True)
-
-#make the visualisations
-data = pd.ExcelFile(file_name_qualitative)
-sheets = data.sheet_names
-col = {'overrepresented' : 'red', 'underrepresented' : 'blue', 'Not significant': 'grey'}
-for sheet in sheets :
- title = 'Proportions of modalities in each clusters with Gower distance and '+sheet+' method'
- df = pd.read_excel(data, sheet)
- legend=''
- for i in range (len(df)):
- if legend == '' :
- pass
- else :
- legend = legend+' ; '
- if df['variables'][i] =='cluster' :
- legend= legend+ str(df['cluster'][i])+' : '+str(round(df['global'][i],2))+'%'
- sunburst = px.sunburst(df, path=['cluster', 'variables', 'modalities'],values='mod/cla',title=title, color = 'signification',color_discrete_map=col)
- sunburst.add_annotation(x=0,y=1.1,text=legend,font = dict(color='black',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=1,text= 'Overrepresented',font = dict(color='red',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.95,text= 'Underrepresented',font = dict(color='blue',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.9,text= 'Not significant',font = dict(color='grey',size=14),showarrow=False)
- sunburst.show()
-
-#move the files in the good directory
-shutil.move(file_name_x2,path+file_name_x2)
-shutil.move(file_name_qualitative,path+file_name_qualitative)
-shutil.move(file_name_weight,path+file_name_weight)
-shutil.move(file_name_anova,path+file_name_anova)
-shutil.move(file_name_quantitative,path+file_name_quantitative)
diff --git a/divis/semantic5.py b/divis/semantic5.py
deleted file mode 100644
index 5e65e883df967a1f372858d5c30034a60a13bb45..0000000000000000000000000000000000000000
--- a/divis/semantic5.py
+++ /dev/null
@@ -1,124 +0,0 @@
-# Data analysis and manipulation library
-import pandas as pd
-import plotly.express as px
-import os
-
-# System library to manipulate the file system
-from os import path
-from scripts.utils import write_excel
-import shutil
-from tqdm import tqdm
-from scripts.quads import *
-
-df = pd.ExcelFile('data/semantic_cluster_coordinates5.xlsx')
-sheets = df.sheet_names
-df1 = pd.read_excel('data/input_data_file.xlsx')
-for sheet in tqdm(sheets) :
- df2 = pd.read_excel(df, sheet)
- #quantitatives variables
- quantitative =['Name (original)','Number of flowers per inflorescence']
- #qualitatives variables
- qualitative = ['Name (original)',
- 'Breeding period',
- 'Geographic origin',
- 'Horticultural group',
- 'Ploidy',
- 'Bush height',
- 'Shape',
- 'Quantity of prickles',
- 'Perfume intensity',
- 'Repeat flowering',
- 'Quantity of bristles by branch',
- 'Shine of upper face',
- 'Corolla form',
- 'Corolla size',
- 'Color repartition',
- 'Duplicature',
- 'Petal color']
-
- df_quali = df1[qualitative]
- df_quanti = df1[quantitative]
-
- #take the variable cluster from the second table
- #with a merge from df1 to df2
- #merge : df1 = Name(original) ; df2 = Unnamed: 0
- #rename the df2 columns from Unnamed: 0 to Name(original) to make the merge
- df2.rename(columns={'Unnamed: 0' : 'Name (original)'}, inplace = True)
- columns_df2 = ['Name (original)','cluster']
- df2 = df2[columns_df2]
-
- #make the dataframe that contain only the qualitatives variables
- dataframe_quali = df_quali.merge(df2)
- dataframe_quali = dataframe_quali.fillna('missing values')
-
- #make the dataframe that contain only the quantitatives variables
- dataframe_quanti = df_quanti.merge(df2)
- dataframe_quanti = dataframe_quanti.rename(columns = {'Number of flowers per inflorescence' : 'Number_of_flowers_per_inflorescence'})
-
- #make the qualitative analysis
- sdqualitative = sdquali(dataframe_quali, qualitative, 'cluster', 0.05)
- sdqualitative=sdqualitative.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
- quali_a = quali_analysis(dataframe_quali, qualitative, 'cluster')
- cm = clamod(quali_a,'cluster')
- mc = modcla(quali_a,'cluster')
- g = globa(quali_a)
- pv = pvalue(quali_a,'cluster')
- test_value = vtest(quali_a,'cluster',0.05)
- test_value=test_value.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
- w = variable_weight(quali_a)
- w=w.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
-
- #make the quantitative analysis for each quantitative variable
- sd = sdquanti(dataframe_quanti,'Number_of_flowers_per_inflorescence', 'cluster')
- sd = sd.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
- quanti_a = quanti_analysis(sd, dataframe_quanti,'Number_of_flowers_per_inflorescence', 'cluster',0.05,0.05)
- quanti_a = quanti_a.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
-
- #out :
- #create the new path for the result
- if not os.path.exists('results/semantic/cluster5') :
- os.makedirs('results/semantic/cluster5')
- path = 'results/semantic/cluster5/'
-
- #name the files
- file_name_x2 = 'x2_semantic_cluster5.xlsx'
- file_name_qualitative = 'qualitative_analysis_semantic_cluster5.xlsx'
- file_name_weight = 'weight_semantic_cluster5.xlsx'
- file_name_anova = 'anova_semantic_cluster5.xlsx'
- file_name_quantitative = 'quantitative_analysis_semantic_cluster5.xlsx'
-
- #create the excel files
- write_excel(file_name_x2, sheet, sdqualitative, idx=True)
- write_excel(file_name_qualitative, sheet, test_value,idx=True)
- write_excel(file_name_weight, sheet, w,idx=True)
- write_excel(file_name_anova, sheet, sd,idx=True)
- write_excel(file_name_quantitative, sheet, quanti_a, idx=True)
-
-#make the visualisations
-data = pd.ExcelFile(file_name_qualitative)
-sheets = data.sheet_names
-col = {'overrepresented' : 'red', 'underrepresented' : 'blue', 'Not significant': 'grey'}
-for sheet in sheets :
- title = 'Proportions of modalities in each clusters with Semantic distance and '+sheet+' method'
- df = pd.read_excel(data, sheet)
- legend=''
- for i in range (len(df)):
- if legend == '' :
- pass
- else :
- legend = legend+' ; '
- if df['variables'][i] =='cluster' :
- legend= legend+ str(df['cluster'][i])+' : '+str(round(df['global'][i],2))+'%'
- sunburst = px.sunburst(df, path=['cluster', 'variables', 'modalities'],values='mod/cla',title=title, color = 'signification',color_discrete_map=col)
- sunburst.add_annotation(x=0,y=1.1,text=legend,font = dict(color='black',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=1,text= 'Overrepresented',font = dict(color='red',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.95,text= 'Underrepresented',font = dict(color='blue',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.9,text= 'Not significant',font = dict(color='grey',size=14),showarrow=False)
- sunburst.show()
-
-#move the files in the good directory
-shutil.move(file_name_x2,path+file_name_x2)
-shutil.move(file_name_qualitative,path+file_name_qualitative)
-shutil.move(file_name_weight,path+file_name_weight)
-shutil.move(file_name_anova,path+file_name_anova)
-shutil.move(file_name_quantitative,path+file_name_quantitative)
diff --git a/divis/semantic6.py b/divis/semantic6.py
deleted file mode 100644
index 7d197bf7b8710f4ef991af714b96e085ca2bd12e..0000000000000000000000000000000000000000
--- a/divis/semantic6.py
+++ /dev/null
@@ -1,124 +0,0 @@
-# Data analysis and manipulation library
-import pandas as pd
-import plotly.express as px
-import os
-
-# System library to manipulate the file system
-from os import path
-from scripts.utils import write_excel
-import shutil
-from tqdm import tqdm
-from scripts.quads import *
-
-df = pd.ExcelFile('data/semantic_cluster_coordinates6.xlsx')
-sheets = df.sheet_names
-df1 = pd.read_excel('data/input_data_file.xlsx')
-for sheet in tqdm(sheets) :
- df2 = pd.read_excel(df, sheet)
- #quantitatives variables
- quantitative =['Name (original)','Number of flowers per inflorescence']
- #qualitatives variables
- qualitative = ['Name (original)',
- 'Breeding period',
- 'Geographic origin',
- 'Horticultural group',
- 'Ploidy',
- 'Bush height',
- 'Shape',
- 'Quantity of prickles',
- 'Perfume intensity',
- 'Repeat flowering',
- 'Quantity of bristles by branch',
- 'Shine of upper face',
- 'Corolla form',
- 'Corolla size',
- 'Color repartition',
- 'Duplicature',
- 'Petal color']
-
- df_quali = df1[qualitative]
- df_quanti = df1[quantitative]
-
- #take the variable cluster from the second table
- #with a merge from df1 to df2
- #merge : df1 = Name(original) ; df2 = Unnamed: 0
- #rename the df2 columns from Unnamed: 0 to Name(original) to make the merge
- df2.rename(columns={'Unnamed: 0' : 'Name (original)'}, inplace = True)
- columns_df2 = ['Name (original)','cluster']
- df2 = df2[columns_df2]
-
- #make the dataframe that contain only the qualitatives variables
- dataframe_quali = df_quali.merge(df2)
- dataframe_quali = dataframe_quali.fillna('missing values')
-
- #make the dataframe that contain only the quantitatives variables
- dataframe_quanti = df_quanti.merge(df2)
- dataframe_quanti = dataframe_quanti.rename(columns = {'Number of flowers per inflorescence' : 'Number_of_flowers_per_inflorescence'})
-
- #make the qualitative analysis
- sdqualitative = sdquali(dataframe_quali, qualitative, 'cluster', 0.05)
- sdqualitative=sdqualitative.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
- quali_a = quali_analysis(dataframe_quali, qualitative, 'cluster')
- cm = clamod(quali_a,'cluster')
- mc = modcla(quali_a,'cluster')
- g = globa(quali_a)
- pv = pvalue(quali_a,'cluster')
- test_value = vtest(quali_a,'cluster',0.05)
- test_value=test_value.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
- w = variable_weight(quali_a)
- w=w.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
-
- #make the quantitative analysis for each quantitative variable
- sd = sdquanti(dataframe_quanti,'Number_of_flowers_per_inflorescence', 'cluster')
- sd = sd.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
- quanti_a = quanti_analysis(sd, dataframe_quanti,'Number_of_flowers_per_inflorescence', 'cluster',0.05,0.05)
- quanti_a = quanti_a.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
-
- #out :
- #create the new path for the result
- if not os.path.exists('results/semantic/cluster6') :
- os.makedirs('results/semantic/cluster6')
- path = 'results/semantic/cluster6/'
-
- #name the files
- file_name_x2 = 'x2_semantic_cluster6.xlsx'
- file_name_qualitative = 'qualitative_analysis_semantic_cluster6.xlsx'
- file_name_weight = 'weight_semantic_cluster6.xlsx'
- file_name_anova = 'anova_semantic_cluster6.xlsx'
- file_name_quantitative = 'quantitative_analysis_semantic_cluster6.xlsx'
-
- #create the excel files
- write_excel(file_name_x2, sheet, sdqualitative, idx=True)
- write_excel(file_name_qualitative, sheet, test_value,idx=True)
- write_excel(file_name_weight, sheet, w,idx=True)
- write_excel(file_name_anova, sheet, sd,idx=True)
- write_excel(file_name_quantitative, sheet, quanti_a, idx=True)
-
-#make the visualisations
-data = pd.ExcelFile(file_name_qualitative)
-sheets = data.sheet_names
-col = {'overrepresented' : 'red', 'underrepresented' : 'blue', 'Not significant': 'grey'}
-for sheet in sheets :
- title = 'Proportions of modalities in each clusters with Semantic distance and '+sheet+' method'
- df = pd.read_excel(data, sheet)
- legend=''
- for i in range (len(df)):
- if legend == '' :
- pass
- else :
- legend = legend+' ; '
- if df['variables'][i] =='cluster' :
- legend= legend+ str(df['cluster'][i])+' : '+str(round(df['global'][i],2))+'%'
- sunburst = px.sunburst(df, path=['cluster', 'variables', 'modalities'],values='mod/cla',title=title, color = 'signification',color_discrete_map=col)
- sunburst.add_annotation(x=0,y=1.1,text=legend,font = dict(color='black',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=1,text= 'Overrepresented',font = dict(color='red',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.95,text= 'Underrepresented',font = dict(color='blue',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.9,text= 'Not significant',font = dict(color='grey',size=14),showarrow=False)
- sunburst.show()
-
-#move the files in the good directory
-shutil.move(file_name_x2,path+file_name_x2)
-shutil.move(file_name_qualitative,path+file_name_qualitative)
-shutil.move(file_name_weight,path+file_name_weight)
-shutil.move(file_name_anova,path+file_name_anova)
-shutil.move(file_name_quantitative,path+file_name_quantitative)
diff --git a/divis/semantic7.py b/divis/semantic7.py
deleted file mode 100644
index cc93fe6f48c13af2e911de919c63e1b95a96153e..0000000000000000000000000000000000000000
--- a/divis/semantic7.py
+++ /dev/null
@@ -1,124 +0,0 @@
-# Data analysis and manipulation library
-import pandas as pd
-import plotly.express as px
-import os
-
-# System library to manipulate the file system
-from os import path
-from scripts.utils import write_excel
-import shutil
-from tqdm import tqdm
-from scripts.quads import *
-
-df = pd.ExcelFile('data/semantic_cluster_coordinates7.xlsx')
-sheets = df.sheet_names
-df1 = pd.read_excel('data/input_data_file.xlsx')
-for sheet in tqdm(sheets) :
- df2 = pd.read_excel(df, sheet)
- #quantitatives variables
- quantitative =['Name (original)','Number of flowers per inflorescence']
- #qualitatives variables
- qualitative = ['Name (original)',
- 'Breeding period',
- 'Geographic origin',
- 'Horticultural group',
- 'Ploidy',
- 'Bush height',
- 'Shape',
- 'Quantity of prickles',
- 'Perfume intensity',
- 'Repeat flowering',
- 'Quantity of bristles by branch',
- 'Shine of upper face',
- 'Corolla form',
- 'Corolla size',
- 'Color repartition',
- 'Duplicature',
- 'Petal color']
-
- df_quali = df1[qualitative]
- df_quanti = df1[quantitative]
-
- #take the variable cluster from the second table
- #with a merge from df1 to df2
- #merge : df1 = Name(original) ; df2 = Unnamed: 0
- #rename the df2 columns from Unnamed: 0 to Name(original) to make the merge
- df2.rename(columns={'Unnamed: 0' : 'Name (original)'}, inplace = True)
- columns_df2 = ['Name (original)','cluster']
- df2 = df2[columns_df2]
-
- #make the dataframe that contain only the qualitatives variables
- dataframe_quali = df_quali.merge(df2)
- dataframe_quali = dataframe_quali.fillna('missing values')
-
- #make the dataframe that contain only the quantitatives variables
- dataframe_quanti = df_quanti.merge(df2)
- dataframe_quanti = dataframe_quanti.rename(columns = {'Number of flowers per inflorescence' : 'Number_of_flowers_per_inflorescence'})
-
- #make the qualitative analysis
- sdqualitative = sdquali(dataframe_quali, qualitative, 'cluster', 0.05)
- sdqualitative=sdqualitative.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
- quali_a = quali_analysis(dataframe_quali, qualitative, 'cluster')
- cm = clamod(quali_a,'cluster')
- mc = modcla(quali_a,'cluster')
- g = globa(quali_a)
- pv = pvalue(quali_a,'cluster')
- test_value = vtest(quali_a,'cluster',0.05)
- test_value=test_value.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
- w = variable_weight(quali_a)
- w=w.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
-
- #make the quantitative analysis for each quantitative variable
- sd = sdquanti(dataframe_quanti,'Number_of_flowers_per_inflorescence', 'cluster')
- sd = sd.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
- quanti_a = quanti_analysis(sd, dataframe_quanti,'Number_of_flowers_per_inflorescence', 'cluster',0.05,0.05)
- quanti_a = quanti_a.rename_axis('file : 20220615_florhige_synthese_english, code : 20220615_quads')
-
- #out :
- #create the new path for the result
- if not os.path.exists('results/semantic/cluster7') :
- os.makedirs('results/semantic/cluster7')
- path = 'results/semantic/cluster7/'
-
- #name the files
- file_name_x2 = 'x2_semantic_cluster7.xlsx'
- file_name_qualitative = 'qualitative_analysis_semantic_cluster7.xlsx'
- file_name_weight = 'weight_semantic_cluster7.xlsx'
- file_name_anova = 'anova_semantic_cluster7.xlsx'
- file_name_quantitative = 'quantitative_analysis_semantic_cluster7.xlsx'
-
- #create the excel files
- write_excel(file_name_x2, sheet, sdqualitative, idx=True)
- write_excel(file_name_qualitative, sheet, test_value,idx=True)
- write_excel(file_name_weight, sheet, w,idx=True)
- write_excel(file_name_anova, sheet, sd,idx=True)
- write_excel(file_name_quantitative, sheet, quanti_a, idx=True)
-
-#make the visualisations
-data = pd.ExcelFile(file_name_qualitative)
-sheets = data.sheet_names
-col = {'overrepresented' : 'red', 'underrepresented' : 'blue', 'Not significant': 'grey'}
-for sheet in sheets :
- title = 'Proportions of modalities in each clusters with Semantic distance and '+sheet+' method'
- df = pd.read_excel(data, sheet)
- legend=''
- for i in range (len(df)):
- if legend == '' :
- pass
- else :
- legend = legend+' ; '
- if df['variables'][i] =='cluster' :
- legend= legend+ str(df['cluster'][i])+' : '+str(round(df['global'][i],2))+'%'
- sunburst = px.sunburst(df, path=['cluster', 'variables', 'modalities'],values='mod/cla',title=title, color = 'signification',color_discrete_map=col)
- sunburst.add_annotation(x=0,y=1.1,text=legend,font = dict(color='black',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=1,text= 'Overrepresented',font = dict(color='red',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.95,text= 'Underrepresented',font = dict(color='blue',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.9,text= 'Not significant',font = dict(color='grey',size=14),showarrow=False)
- sunburst.show()
-
-#move the files in the good directory
-shutil.move(file_name_x2,path+file_name_x2)
-shutil.move(file_name_qualitative,path+file_name_qualitative)
-shutil.move(file_name_weight,path+file_name_weight)
-shutil.move(file_name_anova,path+file_name_anova)
-shutil.move(file_name_quantitative,path+file_name_quantitative)
diff --git a/divis/visu_genetic_groups.py b/divis/visu_genetic_groups.py
deleted file mode 100644
index e96eeba0082f5acd94c5c391f154019584ad3e7e..0000000000000000000000000000000000000000
--- a/divis/visu_genetic_groups.py
+++ /dev/null
@@ -1,51 +0,0 @@
-import plotly.express as px
-import pandas as pd
-
-#ind_ov = df[df['signification'] == 'overrepresented'].index
-#ind_und = df[df['signification'] == 'underrepresented'].index
-#ind_np = df[df['signification'] == 'Not present'].index
-#ind_ns = df[df['signification'] == 'Not significant'].index
-
-#Overrepresented modalities data
-#df_ov = df.copy()
-#df_ov.drop(ind_und,inplace=True)
-#df_ov.drop(ind_np,inplace=True)
-#df_ov.drop(ind_ns,inplace=True)
-#sunburst_over = px.sunburst(df_ov, path=['cluster', 'variables', 'modalities'], values='cla/mod')
-#sunburst_over.show()
-
-#Underrepresented modalities data
-#df_und = df.copy()
-#df_und.drop(ind_ov,inplace=True)
-#df_und.drop(ind_np,inplace=True)
-#df_und.drop(ind_ns,inplace=True)
-#sunburst_under = px.sunburst(df_und, path=['cluster', 'variables', 'modalities'], values='cla/mod')
-#sunburst_under.show()
-
-
-file_name_qualitative = 'results/Genetic groups/qualitative_analysis_GG.xlsx'
-data = pd.ExcelFile(file_name_qualitative)
-col = {'overrepresented' : 'red', 'underrepresented' : 'blue', 'Not significant': 'grey'}
-title = 'Proportions of modalities in each genetic group with semantic distance'
-df = pd.read_excel(data)
-legend=''
-for i in range (len(df)):
- if legend == '' :
- pass
- else :
- legend = legend+' ; '
- if df['variables'][i] =='Genetic group' :
- legend= legend+ str(df['Genetic group'][i])+' : '+str(round(df['global'][i],2))+'%'
-sunburst = px.sunburst(df, path=['Genetic group', 'variables', 'modalities'],values='mod/cla',title=title, color = 'signification',color_discrete_map=col)
-
-sunburst.add_annotation(x=0,y=1.1,text=legend,font = dict(color='black',size=13),showarrow=False)
-sunburst.add_annotation(x=0.2,y=1,text= 'Overrepresented',font = dict(color='red',size=14),showarrow=False)
-sunburst.add_annotation(x=0.2,y=0.95,text= 'Underrepresented',font = dict(color='blue',size=14),showarrow=False)
-sunburst.add_annotation(x=0.2,y=0.9,text= 'Not significant',font = dict(color='grey',size=14),showarrow=False)
-sunburst.show()
- #treemap = px.treemap(df, path=['cluster', 'variables', 'modalities'],values='mod/cla',title=legend, color = 'signification')
- #treemap.update_traces(root_color="lightgrey")
- #treemap.update_layout(margin = dict(t=50, l=25, r=25, b=25))
- #treemap.show()
-
-
diff --git a/divis/visu_gower5.py b/divis/visu_gower5.py
deleted file mode 100644
index 7ec0eb09d0f3a79153402f8f75b893a99a0ad92a..0000000000000000000000000000000000000000
--- a/divis/visu_gower5.py
+++ /dev/null
@@ -1,55 +0,0 @@
-import plotly.express as px
-import pandas as pd
-
-
-#ind_ov = df[df['signification'] == 'overrepresented'].index
-#ind_und = df[df['signification'] == 'underrepresented'].index
-#ind_np = df[df['signification'] == 'Not present'].index
-#ind_ns = df[df['signification'] == 'Not significant'].index
-
-#Overrepresented modalities data
-#df_ov = df.copy()
-#df_ov.drop(ind_und,inplace=True)
-#df_ov.drop(ind_np,inplace=True)
-#df_ov.drop(ind_ns,inplace=True)
-#sunburst_over = px.sunburst(df_ov, path=['cluster', 'variables', 'modalities'], values='cla/mod')
-#sunburst_over.show()
-
-#Underrepresented modalities data
-#df_und = df.copy()
-#df_und.drop(ind_ov,inplace=True)
-#df_und.drop(ind_np,inplace=True)
-#df_und.drop(ind_ns,inplace=True)
-#sunburst_under = px.sunburst(df_und, path=['cluster', 'variables', 'modalities'], values='cla/mod')
-#sunburst_under.show()
-file_name_qualitative = 'results/gower/cluster5/qualitative_analysis_gower_cluster5.xlsx'
-data = pd.ExcelFile(file_name_qualitative)
-col = {'overrepresented' : 'red', 'underrepresented' : 'blue', 'Not significant': 'grey'}
-sheets = data.sheet_names
-for sheet in sheets :
- title = 'Proportions of modalities in each clusters with Gower distance and '+sheet+' method'
- df = pd.read_excel(data, sheet)
- legend=''
- for i in range (len(df)):
- if legend == '' :
- pass
- else :
- legend = legend+' ; '
- if df['variables'][i] =='cluster' :
- legend= legend+ str(df['cluster'][i])+' : '+str(round(df['global'][i],2))+'%'
- sunburst = px.sunburst(df, path=['cluster', 'variables', 'modalities'],values='mod/cla',title=title, color = 'signification',color_discrete_map=col)
-
- sunburst.add_annotation(x=0,y=1.1,text=legend,font = dict(color='black',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=1,text= 'Overrepresented',font = dict(color='red',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.95,text= 'Underrepresented',font = dict(color='blue',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.9,text= 'Not significant',font = dict(color='grey',size=14),showarrow=False)
- sunburst.show()
-
-
-
- #treemap = px.treemap(df, path=['cluster', 'variables', 'modalities'],values='mod/cla',title=legend, color = 'signification')
- #treemap.update_traces(root_color="lightgrey")
- #treemap.update_layout(margin = dict(t=50, l=25, r=25, b=25))
- #treemap.show()
-
-
diff --git a/divis/visu_gower6.py b/divis/visu_gower6.py
deleted file mode 100644
index eeaf9d824c370b03b6629698529b0888dfd1db7f..0000000000000000000000000000000000000000
--- a/divis/visu_gower6.py
+++ /dev/null
@@ -1,54 +0,0 @@
-import plotly.express as px
-import pandas as pd
-
-#ind_ov = df[df['signification'] == 'overrepresented'].index
-#ind_und = df[df['signification'] == 'underrepresented'].index
-#ind_np = df[df['signification'] == 'Not present'].index
-#ind_ns = df[df['signification'] == 'Not significant'].index
-
-#Overrepresented modalities data
-#df_ov = df.copy()
-#df_ov.drop(ind_und,inplace=True)
-#df_ov.drop(ind_np,inplace=True)
-#df_ov.drop(ind_ns,inplace=True)
-#sunburst_over = px.sunburst(df_ov, path=['cluster', 'variables', 'modalities'], values='cla/mod')
-#sunburst_over.show()
-
-#Underrepresented modalities data
-#df_und = df.copy()
-#df_und.drop(ind_ov,inplace=True)
-#df_und.drop(ind_np,inplace=True)
-#df_und.drop(ind_ns,inplace=True)
-#sunburst_under = px.sunburst(df_und, path=['cluster', 'variables', 'modalities'], values='cla/mod')
-#sunburst_under.show()
-
-
-file_name_qualitative = 'results/gower/cluster6/qualitative_analysis_gower_cluster6.xlsx'
-data = pd.ExcelFile(file_name_qualitative)
-col = {'overrepresented' : 'red', 'underrepresented' : 'blue', 'Not significant': 'grey'}
-sheets = data.sheet_names
-for sheet in sheets :
- title = 'Proportions of modalities in each clusters with Gower distance and '+sheet+' method'
- df = pd.read_excel(data, sheet)
- legend=''
- for i in range (len(df)):
- if legend == '' :
- pass
- else :
- legend = legend+' ; '
- if df['variables'][i] =='cluster' :
- legend= legend+ str(df['cluster'][i])+' : '+str(round(df['global'][i],2))+'%'
- sunburst = px.sunburst(df, path=['cluster', 'variables', 'modalities'],values='mod/cla',title=title, color = 'signification',color_discrete_map=col)
-
- sunburst.add_annotation(x=0,y=1.1,text=legend,font = dict(color='black',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=1,text= 'Overrepresented',font = dict(color='red',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.95,text= 'Underrepresented',font = dict(color='blue',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.9,text= 'Not significant',font = dict(color='grey',size=14),showarrow=False)
- sunburst.show()
-
- #treemap = px.treemap(df, path=['cluster', 'variables', 'modalities'],values='mod/cla',title=legend, color = 'signification')
- #treemap.update_traces(root_color="lightgrey")
- #treemap.update_layout(margin = dict(t=50, l=25, r=25, b=25))
- #treemap.show()
-
-
diff --git a/divis/visu_gower7.py b/divis/visu_gower7.py
deleted file mode 100644
index 58241817c5ff4fb38a2b6dbc627a68614a9995c4..0000000000000000000000000000000000000000
--- a/divis/visu_gower7.py
+++ /dev/null
@@ -1,53 +0,0 @@
-import plotly.express as px
-import pandas as pd
-
-#ind_ov = df[df['signification'] == 'overrepresented'].index
-#ind_und = df[df['signification'] == 'underrepresented'].index
-#ind_np = df[df['signification'] == 'Not present'].index
-#ind_ns = df[df['signification'] == 'Not significant'].index
-
-#Overrepresented modalities data
-#df_ov = df.copy()
-#df_ov.drop(ind_und,inplace=True)
-#df_ov.drop(ind_np,inplace=True)
-#df_ov.drop(ind_ns,inplace=True)
-#sunburst_over = px.sunburst(df_ov, path=['cluster', 'variables', 'modalities'], values='cla/mod')
-#sunburst_over.show()
-
-#Underrepresented modalities data
-#df_und = df.copy()
-#df_und.drop(ind_ov,inplace=True)
-#df_und.drop(ind_np,inplace=True)
-#df_und.drop(ind_ns,inplace=True)
-#sunburst_under = px.sunburst(df_und, path=['cluster', 'variables', 'modalities'], values='cla/mod')
-#sunburst_under.show()
-
-
-file_name_qualitative = 'results/gower/cluster7/qualitative_analysis_gower_cluster7.xlsx'
-data = pd.ExcelFile(file_name_qualitative)
-col = {'overrepresented' : 'red', 'underrepresented' : 'blue', 'Not significant': 'grey'}
-sheets = data.sheet_names
-for sheet in sheets :
- title = 'Proportions of modalities in each clusters with Gower distance and '+sheet+' method'
- df = pd.read_excel(data, sheet)
- legend=''
- for i in range (len(df)):
- if legend == '' :
- pass
- else :
- legend = legend+' ; '
- if df['variables'][i] =='cluster' :
- legend= legend+ str(df['cluster'][i])+' : '+str(round(df['global'][i],2))+'%'
- sunburst = px.sunburst(df, path=['cluster', 'variables', 'modalities'],values='mod/cla',title=title, color = 'signification',color_discrete_map=col)
-
- sunburst.add_annotation(x=0,y=1.1,text=legend,font = dict(color='black',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=1,text= 'Overrepresented',font = dict(color='red',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.95,text= 'Underrepresented',font = dict(color='blue',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.9,text= 'Not significant',font = dict(color='grey',size=14),showarrow=False)
- sunburst.show()
- #treemap = px.treemap(df, path=['cluster', 'variables', 'modalities'],values='mod/cla',title=legend, color = 'signification')
- #treemap.update_traces(root_color="lightgrey")
- #treemap.update_layout(margin = dict(t=50, l=25, r=25, b=25))
- #treemap.show()
-
-
diff --git a/divis/visu_semantic5.py b/divis/visu_semantic5.py
deleted file mode 100644
index c93a48fb1a46ffcbca31ebbe0b3dd47727360722..0000000000000000000000000000000000000000
--- a/divis/visu_semantic5.py
+++ /dev/null
@@ -1,55 +0,0 @@
-import plotly.express as px
-import pandas as pd
-
-#ind_ov = df[df['signification'] == 'overrepresented'].index
-#ind_und = df[df['signification'] == 'underrepresented'].index
-#ind_np = df[df['signification'] == 'Not present'].index
-#ind_ns = df[df['signification'] == 'Not significant'].index
-
-#Overrepresented modalities data
-#df_ov = df.copy()
-#df_ov.drop(ind_und,inplace=True)
-#df_ov.drop(ind_np,inplace=True)
-#df_ov.drop(ind_ns,inplace=True)
-#sunburst_over = px.sunburst(df_ov, path=['cluster', 'variables', 'modalities'], values='cla/mod')
-#sunburst_over.show()
-
-#Underrepresented modalities data
-#df_und = df.copy()
-#df_und.drop(ind_ov,inplace=True)
-#df_und.drop(ind_np,inplace=True)
-#df_und.drop(ind_ns,inplace=True)
-#sunburst_under = px.sunburst(df_und, path=['cluster', 'variables', 'modalities'], values='cla/mod')
-#sunburst_under.show()
-
-
-file_name_qualitative = 'results/semantic/cluster5/qualitative_analysis_semantic_cluster5.xlsx'
-data = pd.ExcelFile(file_name_qualitative)
-col = {'overrepresented' : 'red', 'underrepresented' : 'blue', 'Not significant': 'grey'}
-sheets = data.sheet_names
-for sheet in sheets :
- title = 'Proportions of modalities in each clusters with Semantic distance and '+sheet+' method'
- df = pd.read_excel(data, sheet)
- legend=''
- for i in range (len(df)):
- if legend == '' :
- pass
- else :
- legend = legend+' ; '
- if df['variables'][i] =='cluster' :
- legend= legend+ str(df['cluster'][i])+' : '+str(round(df['global'][i],2))+'%'
- sunburst = px.sunburst(df, path=['cluster', 'variables', 'modalities'],values='mod/cla',title=title, color = 'signification',color_discrete_map=col)
- sunburst.add_annotation(x=0,y=1.1,text=legend,font = dict(color='black',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=1,text= 'Overrepresented',font = dict(color='red',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.95,text= 'Underrepresented',font = dict(color='blue',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.9,text= 'Not significant',font = dict(color='grey',size=14),showarrow=False)
- sunburst.show()
-
-
-
- #treemap = px.treemap(df, path=['cluster', 'variables', 'modalities'],values='mod/cla',title=legend, color = 'signification')
- #treemap.update_traces(root_color="lightgrey")
- #treemap.update_layout(margin = dict(t=50, l=25, r=25, b=25))
- #treemap.show()
-
-
diff --git a/divis/visu_semantic6.py b/divis/visu_semantic6.py
deleted file mode 100644
index 9446f872df5e03fc6a27327ca71243d7d0b7f97c..0000000000000000000000000000000000000000
--- a/divis/visu_semantic6.py
+++ /dev/null
@@ -1,52 +0,0 @@
-import plotly.express as px
-import pandas as pd
-
-#ind_ov = df[df['signification'] == 'overrepresented'].index
-#ind_und = df[df['signification'] == 'underrepresented'].index
-#ind_np = df[df['signification'] == 'Not present'].index
-#ind_ns = df[df['signification'] == 'Not significant'].index
-
-#Overrepresented modalities data
-#df_ov = df.copy()
-#df_ov.drop(ind_und,inplace=True)
-#df_ov.drop(ind_np,inplace=True)
-#df_ov.drop(ind_ns,inplace=True)
-#sunburst_over = px.sunburst(df_ov, path=['cluster', 'variables', 'modalities'], values='cla/mod')
-#sunburst_over.show()
-
-#Underrepresented modalities data
-#df_und = df.copy()
-#df_und.drop(ind_ov,inplace=True)
-#df_und.drop(ind_np,inplace=True)
-#df_und.drop(ind_ns,inplace=True)
-#sunburst_under = px.sunburst(df_und, path=['cluster', 'variables', 'modalities'], values='cla/mod')
-#sunburst_under.show()
-
-file_name_qualitative = 'results/semantic/cluster6/qualitative_analysis_semantic_cluster6.xlsx'
-data = pd.ExcelFile(file_name_qualitative)
-col = {'overrepresented' : 'red', 'underrepresented' : 'blue', 'Not significant': 'grey'}
-sheets = data.sheet_names
-for sheet in sheets :
- title = 'Proportions of modalities in each clusters with Semantic distance and '+sheet+' method'
- df = pd.read_excel(data, sheet)
- legend=''
- for i in range (len(df)):
- if legend == '' :
- pass
- else :
- legend = legend+' ; '
- if df['variables'][i] =='cluster' :
- legend= legend+ str(df['cluster'][i])+' : '+str(round(df['global'][i],2))+'%'
- sunburst = px.sunburst(df, path=['cluster', 'variables', 'modalities'],values='mod/cla',title=title, color = 'signification',color_discrete_map=col)
- sunburst.add_annotation(x=0,y=1.1,text=legend,font = dict(color='black',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=1,text= 'Overrepresented',font = dict(color='red',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.95,text= 'Underrepresented',font = dict(color='blue',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.9,text= 'Not significant',font = dict(color='grey',size=14),showarrow=False)
- sunburst.show()
-
- #treemap = px.treemap(df, path=['cluster', 'variables', 'modalities'],values='mod/cla',title=legend, color = 'signification')
- #treemap.update_traces(root_color="lightgrey")
- #treemap.update_layout(margin = dict(t=50, l=25, r=25, b=25))
- #treemap.show()
-
-
diff --git a/divis/visu_semantic7.py b/divis/visu_semantic7.py
deleted file mode 100644
index 975228bacdc52ea223eb90a0ee5d5f1a8852e0db..0000000000000000000000000000000000000000
--- a/divis/visu_semantic7.py
+++ /dev/null
@@ -1,52 +0,0 @@
-import plotly.express as px
-import pandas as pd
-
-#ind_ov = df[df['signification'] == 'overrepresented'].index
-#ind_und = df[df['signification'] == 'underrepresented'].index
-#ind_np = df[df['signification'] == 'Not present'].index
-#ind_ns = df[df['signification'] == 'Not significant'].index
-
-#Overrepresented modalities data
-#df_ov = df.copy()
-#df_ov.drop(ind_und,inplace=True)
-#df_ov.drop(ind_np,inplace=True)
-#df_ov.drop(ind_ns,inplace=True)
-#sunburst_over = px.sunburst(df_ov, path=['cluster', 'variables', 'modalities'], values='cla/mod')
-#sunburst_over.show()
-
-#Underrepresented modalities data
-#df_und = df.copy()
-#df_und.drop(ind_ov,inplace=True)
-#df_und.drop(ind_np,inplace=True)
-#df_und.drop(ind_ns,inplace=True)
-#sunburst_under = px.sunburst(df_und, path=['cluster', 'variables', 'modalities'], values='cla/mod')
-#sunburst_under.show()
-
-file_name_qualitative = 'results/semantic/cluster7/qualitative_analysis_semantic_cluster7.xlsx'
-data = pd.ExcelFile(file_name_qualitative)
-col = {'overrepresented' : 'red', 'underrepresented' : 'blue', 'Not significant': 'grey'}
-sheets = data.sheet_names
-for sheet in sheets :
- title = 'Proportions of modalities in each clusters with Semantic distance and '+sheet+' method'
- df = pd.read_excel(data, sheet)
- legend=''
- for i in range (len(df)):
- if legend == '' :
- pass
- else :
- legend = legend+' ; '
- if df['variables'][i] =='cluster' :
- legend= legend+ str(df['cluster'][i])+' : '+str(round(df['global'][i],2))+'%'
- sunburst = px.sunburst(df, path=['cluster', 'variables', 'modalities'],values='mod/cla',title=title, color = 'signification',color_discrete_map=col)
- sunburst.add_annotation(x=0,y=1.1,text=legend,font = dict(color='black',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=1,text= 'Overrepresented',font = dict(color='red',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.95,text= 'Underrepresented',font = dict(color='blue',size=14),showarrow=False)
- sunburst.add_annotation(x=0.2,y=0.9,text= 'Not significant',font = dict(color='grey',size=14),showarrow=False)
- sunburst.show()
-
- #treemap = px.treemap(df, path=['cluster', 'variables', 'modalities'],values='mod/cla',title=legend, color = 'signification')
- #treemap.update_traces(root_color="lightgrey")
- #treemap.update_layout(margin = dict(t=50, l=25, r=25, b=25))
- #treemap.show()
-
-