def get_users_table():
u = CsvL.get_users_anag()
f = CsvL.get_customers_anag()
p = CsvL.get_province()
r = CsvL.get_regions()
ur = CsvL.get_user_roles()
f = f[['Id', 'Code', 'PdcCode', 'Province']]
f = f.rename(columns={'Id': 'FarmaId'})
f = f.rename(columns={'Province': 'ProvId'})
p = p.drop(['Id', 'Nome', 'Longitudine'], axis=1)
p = p[['Id_Regione', 'Sigla_automobilistica', 'Latitudine']]
p = p.rename(columns={'Sigla_automobilistica': 'ProvId'})
# r['Nome'] = r.Nome.apply(lambda n: n[0:4])
ur = ur.drop(['Id', 'CreatorUserId', 'TenantId'], axis=1)
# alcuni utenti tipo 208 hanno più di un ruolo
ur = ur.groupby('UserId')['RoleId'].last().reset_index()
uf = pd.merge(u, f, left_on=['ClientCode', 'PdcCode'],
right_on=['Code', 'PdcCode'], how='left')
ufp = pd.merge(uf, p)
ufpr = pd.merge(ufp, r)
ufprr = pd.merge(ufpr, ur)
ufprr.drop(['Id_Regione'], axis=1, inplace=True)
ufprr.rename(columns={'Nome': 'Regione'}, inplace=True)
ufprr.drop(['Code', 'PdcCode'], axis=1, inplace=True)
ufprr = ufprr[ufprr.UserId != 12] # Andrea Dini
return ufprr
def add_avatar_data(df, cut_pce=[]):
avatar_pce = CsvL.get_avatar_pce()
av_anag = CsvL.get_avatar_anag()
avatar_pce = pd.merge(avatar_pce,
av_anag,
left_on='AvatarId',
right_on='AvatarId')
if len(cut_pce) > 0:
avatar_pce = avatar_pce[~avatar_pce.AvatarPce.isin(cut_pce)]
on_col = __av_merge_col(df)
df = pd.merge(df, avatar_pce, on=on_col, how='left')
df = df[~df.AvSessId.isnull()]
return df
def get_df_group_prod(include_rare=False):
df = get_df()
p_anag = CsvL.get_prod_anag()
feat_df = df.groupby('ProductId').apply(lambda x: pd.Series(
{
'nUsers': x.UserId.nunique(),
'nFarma': x.FarmaId.nunique(),
'nProv': x.ProvId.nunique(),
'nReg': x.Regione.nunique(),
'nAvSess': x.AvSessId.nunique(),
'nSess': x.SessionId.nunique(),
'nTot': x.Id.count(),
'MedianPce': x.AvatarPce.median(),
'MeanPce': x.AvatarPce.mean(),
'nRight': sum(x.ActionType == "RightProduct"),
'NordSud': x.Latitudine.mean() - 42,
# 'LatVar': x.Latitudine.var(),
'UserRatio': x.Id.count() / x.UserId.nunique(),
'Ratio': sum(x.ActionType == 'RightProduct') / x.Id.count(),
'Recency': (dm.MAXDATE - x.YMD.max()).days + 1,
'Frequency': x.YMD.nunique()
})).reset_index()
prod = pd.merge(p_anag, feat_df)
if not include_rare:
prod = prod[prod.nTot > 2].reset_index(drop=True)
return prod
def get_df(max_date=-1):
df = CsvL.get_avatar_info()
df = dh.add_avatar_data(df, cut_pce=[5, 6, 7])
df = dh.add_session_date(df)
df.drop(['AvatarId'], axis=1, inplace=True)
df = dm.filter_date(df, 'YMD', max_date)
df = Users.merge_users_clean(df)
# filtro colonne per primo test sensibilita
df = df.drop(['Age', 'YearMonth', 'ClientCode', 'FarmaId', 'Latitudine'],
axis=1)
return df
def get_df(max_date=-1):
df = CsvL.get_prod_history()
df = dh.add_avatar_data(df, cut_pce=[5, 6, 7])
__hist_hardfix(df)
df = dh.add_session_date(df)
df.drop(['AvatarId'], axis=1, inplace=True)
df = dm.filter_date(df, 'YMD', max_date)
df = Users.merge_users_clean(df)
df = df[[
'Id', 'UserId', 'SessionId', 'ActionType', 'ProductId', 'AvSessId',
'AvatarPce', 'YMD', 'NameSurname', 'Regione', 'RoleId', 'FarmaId',
'Latitudine', 'ProvId', 'Sex'
]]
df = dh.add_prod_name(df)
return df
def plot_uhist(uid, i_uh, arr_start):
i_uh_r = i_uh.rolling(10)
i_sumR = i_uh_r.RightCount.sum()
i_sumT = i_uh_r.nTot.sum()
i_movavg = i_sumR / i_sumT
r_obs = range(0, len(i_movavg))
r_obs2 = np.arange(-0.7, len(i_movavg) - 0.7, 1)
f = plt.figure(figsize=(9, 8))
ax = f.add_subplot(111)
ax2 = ax.twinx()
l_hand = []
l_lab = []
line_avg, = ax.plot(r_obs,
i_movavg,
lw=3,
zorder=10,
color=co.ab_colors['rosso'])
bar_ratio = ax.bar(r_obs2,
i_uh.Ratio,
color=co.ab_colors['azzurro'],
alpha=0.5,
width=0.7,
align='edge',
zorder=1)
bar_ntot = ax2.bar(r_obs,
i_uh.nTot,
color=co.ab_colors['verde'],
alpha=0.5,
width=0.25,
align='edge')
weblog = CsvL.get_web_log(uid)
ax.set_zorder(ax2.get_zorder() + 1)
ax.patch.set_visible(False)
l_hand.append(line_avg)
l_lab.append('Rolling average')
l_hand.append(bar_ratio)
l_lab.append('Correctness')
l_hand.append(bar_ntot)
l_lab.append('Number of products')
if weblog is not None:
num_web_check = __count_occurrences(arr_start.values, weblog)
xval = np.add(np.where(num_web_check > 0), 0.25).squeeze(axis=0)
yval = np.ones(len(xval)) * 0.5
sca_web = ax.scatter(xval,
yval,
marker='d',
edgecolors='k',
s=150,
lw=1,
facecolor=co.ab_colors['giallo'],
zorder=2)
l_hand.append(sca_web)
l_lab.append('Website check')
ax.legend(tuple(l_hand), tuple(l_lab), fontsize=16)
ax.set_ylabel('% of correct recommendations', size=18)
ax2.set_ylabel('Number of recommended products', size=18)
ax.set_xlabel('Sessions', size=18)
ax.set_xticks(r_obs)
ax.tick_params(labelsize=16)
vals = [0, 0.25, 0.5, 0.75, 1]
ax.set_yticks(vals)
ax.yaxis.set_major_formatter(ticker.PercentFormatter())
ax.set_yticklabels(['{:,.0%}'.format(x) for x in vals])
ax2.tick_params(labelsize=16)
yticks = np.arange(0, i_uh.nTot.max(), 5)
yticks = np.append(yticks, i_uh.nTot.max())
ax2.set_yticks(yticks)
ax2.yaxis.set_major_formatter(ticker.ScalarFormatter())
lbl = arr_start.dt.strftime('%d/%m/%Y')
ax.set_xticklabels(lbl, rotation=45, ha='right', size=15)
plt.title("Performance history for user"
" {0}".format(Users.get_user_name(uid)),
size=25,
y=1.02)
def add_session_date(df):
ah = CsvL.get_avatar_history()
df = pd.merge(df, ah, on=['AvatarId', 'SessionId', 'UserId'])
return df
def add_prod_name(df):
p_anag = CsvL.get_prod_anag()
p_anag = p_anag[['ProductId', 'ProdName']]
df = pd.merge(df, p_anag, left_on='ProductId', right_on='ProductId')
return df
def get_user_name(user_id):
u = CsvL.get_users_anag()
ret = u[u.UserId == user_id].NameSurname.values[0]
return ret
def get_product_name(product_id):
p = CsvL.get_prod_anag()
ret = p[p.ProductId == product_id].ProdName.values[0]
return ret