ajoubrel-ensae/BDC-team-1
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

final changes for spider charts

Browse Source
This commit is contained in:
Thomas PIQUE 2024-03-31 21:59:52 +00:00
parent b9a3d05a2f
commit 52b39e03be
2 changed files with 138 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

128
Sport/Modelization/segment_analysis_sport_0_6.ipynb
View File

File diff suppressed because one or more lines are too long

22
utils_segmentation.py
View File

@ -140,22 +140,27 @@ def radar_mp_plot(df, categories, index) :
def radar_mp_plot_all(df, type_of_activity) : def radar_mp_plot_all(df, type_of_activity) :
# table summarizing variables relative to marketing personae # table summarizing variables relative to marketing personae
df_mp = df.groupby("segment")[["gender_female", "gender_male", "gender_other", "country_fr"]].mean().reset_index() df_mp = df.groupby("segment")[["gender_female", "gender_male", "gender_other", "age"]].mean().reset_index()
df_mp.insert(3, "share_known_gender", df_mp["gender_female"]+df_mp["gender_male"]) #df_mp.insert(3, "share_known_gender", df_mp["gender_female"]+df_mp["gender_male"])
df_mp.insert(4, "share_of_women", df_mp["gender_female"]/(df_mp["share_known_gender"])) df_mp.insert(4, "share_of_women", df_mp["gender_female"]/(df_mp["gender_female"]+df_mp["gender_male"]))
# table relative to purchasing behaviour # table relative to purchasing behaviour
df_pb = df.groupby("segment")[["prop_purchases_internet", "taux_ouverture_mail", "opt_in"]].mean().reset_index() df_pb = df.groupby("segment")[["prop_purchases_internet", "taux_ouverture_mail", "opt_in"]].mean().reset_index()
# concatenation of tables to prepare the plot # concatenation of tables to prepare the plot
df_used = pd.concat([df_pb, df_mp[['share_known_gender', 'share_of_women', 'country_fr']]], axis=1) df_used = pd.concat([df_pb, df_mp[[ 'share_of_women', 'age']]], axis=1)
# rename columns for the plot
df_used = df_used.rename(columns={'taux_ouverture_mail': 'mails_opened', 'prop_purchases_internet': 'purchases_internet'})
# visualization # visualization
nb_segments = df_used.shape[0] nb_segments = df_used.shape[0]
categories = list(df_used.drop("segment", axis=1).columns) categories = list(df_used.drop("segment", axis=1).columns)
var_not_perc = ["age"]
# Initialize graphic # Initialize graphic
fig, ax = plt.subplots(2,2, figsize=(25, 20), subplot_kw=dict(polar=True)) fig, ax = plt.subplots(2,2, figsize=(20, 20), subplot_kw=dict(polar=True))
for index in range(nb_segments) : for index in range(nb_segments) :
row = index // 2 # Division entière pour obtenir le numéro de ligne row = index // 2 # Division entière pour obtenir le numéro de ligne
@ -195,7 +200,10 @@ def radar_mp_plot_all(df, type_of_activity) :
# labels # labels
ax[row, col].set_yticklabels([]) ax[row, col].set_yticklabels([])
ax[row, col].set_xticks(angles) ax[row, col].set_xticks(angles)
ticks = [categories[i].replace("_"," ") + f"\n({round(100 * tvalues[i],2)}%)" for i in range(len(categories))]
# define the ticks
values_printed = [str(round(tvalues[i],2)) if categories[i] in var_not_perc else f"{round(100 * tvalues[i],2)}%" for i in range(len(categories))]
ticks = [categories[i].replace("_"," ") + f"\n({values_printed[i]})" for i in range(len(categories))]
ax[row, col].set_xticklabels(ticks, color="black", size = 20) ax[row, col].set_xticklabels(ticks, color="black", size = 20)
ax[row, col].spines['polar'].set_visible(False) ax[row, col].spines['polar'].set_visible(False)
@ -203,6 +211,8 @@ def radar_mp_plot_all(df, type_of_activity) :
ax[row, col].set_title(f'Segment {index+1}\n', size = 24) ax[row, col].set_title(f'Segment {index+1}\n', size = 24)
fig.suptitle(f"Characteristics of marketing personae of {type_of_activity} companies", size=32) fig.suptitle(f"Characteristics of marketing personae of {type_of_activity} companies", size=32)
plt.tight_layout()
# plt.show() # plt.show()
def known_sociodemo_caracteristics(df, type_of_activity) : def known_sociodemo_caracteristics(df, type_of_activity) :