def run_predict(model_name, path_model, path_data, path_output, n_sample=-1):
path_output = root + path_output
path_data = root + path_data + "/features.zip" #.zip
path_model = root + path_model
path_pipeline = path_model + "/pipeline/"
path_test_X = path_data + "/features.zip" #.zip #added path to testing features
log(path_data, path_model, path_output)
colid = load(f'{path_pipeline}/colid.pkl')
df = load_dataset(path_data,
path_data_y=None,
colid=colid,
n_sample=n_sample)
dfX, cols_family = preprocess(df, path_pipeline)
ypred, yproba = predict(model_name, path_model, dfX, cols_family)
log("Saving prediction", ypred.shape, path_output)
os.makedirs(path_output, exist_ok=True)
df[cols_family["coly"] + "_pred"] = ypred
if yproba is not None:
df[cols_family["coly"] + "_pred_proba"] = yproba
df.to_csv(f"{path_output}/prediction.csv")
log(df.head(8))
##### Export Specific
df[cols_family["coly"]] = ypred
df[[cols_family["coly"]]].to_csv(f"{path_output}/pred_only.csv")
def run_predict(config_name,
config_path,
n_sample=-1,
path_data=None,
path_output=None,
pars={},
model_dict=None):
model_dict = model_dict_load(model_dict,
config_path,
config_name,
verbose=True)
m = model_dict['global_pars']
model_class = model_dict['model_pars']['model_class']
path_data = m['path_pred_data'] if path_data is None else path_data
path_pipeline = m['path_pred_pipeline'] # path_output + "/pipeline/" )
path_model = m['path_pred_model']
path_output = m['path_pred_output'] if path_output is None else path_output
log(path_data, path_model, path_output)
pars = {
'cols_group': model_dict['data_pars']['cols_input_type'],
'pipe_list': model_dict['model_pars']['pre_process_pars']['pipe_list']
}
##########################################################################################
colid = load(f'{path_pipeline}/colid.pkl')
df = load_dataset(path_data,
path_data_y=None,
colid=colid,
n_sample=n_sample)
from run_preprocess import preprocess_inference as preprocess
dfX, cols_family = preprocess(df, path_pipeline, preprocess_pars=pars)
ypred, yproba = predict(model_class, path_model, dfX, cols_family)
log("############ Saving prediction ###################################################"
)
log(ypred.shape, path_output)
os.makedirs(path_output, exist_ok=True)
df[cols_family["coly"] + "_pred"] = ypred
if yproba is not None:
df[cols_family["coly"] + "_pred_proba"] = yproba
df.to_csv(f"{path_output}/prediction.csv")
log(df.head(8))
log("########### Export Specific ######################################################"
)
df[cols_family["coly"]] = ypred
df[[cols_family["coly"]]].to_csv(f"{path_output}/pred_only.csv")
def run_data_check(path_data,
path_data_ref,
path_model,
path_output,
sample_ratio=0.5):
"""
Calcualata Dataset Shift before prediction.
"""
from run_preprocess import preprocess_inference as preprocess
path_output = root + path_output
path_data = root + path_data
path_data_ref = root + path_data_ref
path_pipeline = root + path_model + "/pipeline/"
os.makedirs(path_output, exist_ok=True)
colid = load(f'{path_pipeline}/colid.pkl')
df1 = load_dataset(path_data_ref, colid=colid)
dfX1, cols_family1 = preprocess(df1, path_pipeline)
df2 = load_dataset(path_data, colid=colid)
dfX2, cols_family2 = preprocess(df2, path_pipeline)
colsX = cols_family1["colnum_bin"] + cols_family1["colcat_bin"]
dfX1 = dfX1[colsX]
dfX2 = dfX2[colsX]
from util_feature import pd_stat_dataset_shift
nsample = int(min(len(dfX1), len(dfX2)) * sample_ratio)
metrics_psi = pd_stat_dataset_shift(dfX2,
dfX1,
colsX,
nsample=nsample,
buckets=7,
axis=0)
metrics_psi.to_csv(f"{path_output}/prediction_features_metrics.csv")
log(metrics_psi)
def preprocess(path_train_X="",
path_train_y="",
path_pipeline_export="",
cols_group=None,
n_sample=5000,
preprocess_pars={},
path_features_store=None):
"""
Used for trainiing only
Save params on disk
:param path_train_X:
:param path_train_y:
:param path_pipeline_export:
:param cols_group:
:param n_sample:
:param preprocess_pars:
:param path_features_store:
:return:
"""
##### column names for feature generation #####################################################
log(cols_group)
coly = cols_group['coly'] # 'salary'
colid = cols_group['colid'] # "jobId"
colcat = cols_group[
'colcat'] # [ 'companyId', 'jobType', 'degree', 'major', 'industry' ]
colnum = cols_group['colnum'] # ['yearsExperience', 'milesFromMetropolis']
os.makedirs(path_pipeline_export, exist_ok=True)
log(path_pipeline_export)
save(colid, f'{path_pipeline_export}/colid.pkl')
### Pipeline Execution ##########################################
pipe_default = [{
'uri': 'source/prepro.py::pd_coly',
'pars': {},
'cols_family': 'coly',
'type': 'coly'
}, {
'uri': 'source/prepro.py::pd_colnum_bin',
'pars': {},
'cols_family': 'colnum',
'type': ''
}, {
'uri': 'source/prepro.py::pd_colnum_binto_onehot',
'pars': {},
'cols_family': 'colnum_bin',
'type': ''
}, {
'uri': 'source/prepro.py::pd_colcat_bin',
'pars': {},
'cols_family': 'colcat',
'type': ''
}, {
'uri': 'source/prepro.py::pd_colcat_to_onehot',
'pars': {},
'cols_family': 'colcat_bin',
'type': ''
}, {
'uri': 'source/prepro.py::pd_colcross',
'pars': {},
'cols_family': 'colcross',
'type': 'cross'
}]
pipe_list = preprocess_pars.get('pipe_list', pipe_default)
pipe_list_X = [
task for task in pipe_list
if task.get('type', '') not in ['coly', 'filter']
]
pipe_list_y = [
task for task in pipe_list if task.get('type', '') in ['coly']
]
pipe_filter = [
task for task in pipe_list if task.get('type', '') in ['filter']
]
##### Load data #################################################################################
df = load_dataset(path_train_X, path_train_y, colid, n_sample=n_sample)
##### Generate features ##########################################################################
dfi_all = {} ### Dict of all features
cols_family_all = {'colid': colid, 'colnum': colnum, 'colcat': colcat}
if len(pipe_filter) > 0:
log("##### Filter #########################################################################"
)
pipe_i = pipe_filter[0]
pipe_fun = load_function_uri(pipe_i['uri'])
df, col_pars = pipe_fun(df,
list(df.columns),
pars=pipe_i.get('pars', {}))
if len(pipe_list_y) > 0:
log("##### coly ###########################################################################"
)
pipe_i = pipe_list_y[0]
pipe_fun = load_function_uri(pipe_i['uri'])
logs("----------df----------\n", df)
pars = pipe_i.get('pars', {})
pars['path_features_store'] = path_features_store
pars['path_pipeline_export'] = path_pipeline_export
df, col_pars = pipe_fun(df, cols_group['coly'],
pars=pars) ### coly can remove rows
logs("----------df----------\n", df)
dfi_all['coly'] = df[cols_group['coly']]
cols_family_all['coly'] = cols_group['coly']
save_features(df[cols_group['coly']], "coly",
path_features_store) ### already saved
save(coly, f'{path_pipeline_export}/coly.pkl')
##### Processors ###############################################################################
dfi_all['coly'] = df[cols_group['coly']]
#for colg, colg_list in cols_group.items() :
# if colg not in ['colid']:
# dfi_all[colg] = df[colg_list] ## colnum colcat, coly
for pipe_i in pipe_list_X:
log("###################", pipe_i,
"##########################################################")
pipe_fun = load_function_uri(
pipe_i['uri']) ### Load the code definition into pipe_fun
cols_name = pipe_i['cols_family']
col_type = pipe_i['type']
pars = pipe_i.get('pars', {})
pars[
'path_features_store'] = path_features_store ### intermdiate dataframe
pars['path_pipeline_export'] = path_pipeline_export ### Store pipeline
if col_type == 'cross':
log("################### Adding Cross ###################################################"
)
pars['dfnum_hot'] = dfi_all[
'colnum_onehot'] ### dfnum_hot --> dfcross
pars['dfcat_hot'] = dfi_all['colcat_onehot']
pars['colid'] = colid
pars['colcross_single'] = cols_group.get('colcross', [])
elif col_type == 'add_coly':
log('add_coly genetic', cols_group['coly'])
pars['coly'] = cols_group['coly']
pars['dfy'] = dfi_all['coly'] ### Transformed dfy
### Input columns or prevously Computed Columns ( colnum_bin )
cols_list = cols_group[cols_name] if cols_name in cols_group else list(
dfi_all[cols_name].columns)
df_ = df[cols_list] if cols_name in cols_group else dfi_all[cols_name]
#cols_list = list(dfi_all[cols_name].columns)
#df_ = dfi_all[cols_name]
dfi, col_pars = pipe_fun(df_, cols_list, pars=pars)
### Concatenate colnum, colnum_bin into cols_family_all , dfi_all ###########################
for colj, colist in col_pars['cols_new'].items():
### Merge sub-family
cols_family_all[colj] = cols_family_all.get(colj, []) + colist
dfi_all[colj] = pd.concat(
(dfi_all[colj], dfi), axis=1) if colj in dfi_all else dfi
# save_features(dfi_all[colj], colj, path_features_store)
###### Merge AlL int dfXy ##################################################################
dfXy = df[[coly] + colnum + colcat]
#dfXy = df[ [coly] ]
for t in dfi_all.keys():
if t not in ['coly', 'colnum', 'colcat']:
dfXy = pd.concat((dfXy, dfi_all[t]), axis=1)
save_features(dfXy, 'dfX', path_features_store)
colXy = list(dfXy.columns)
colXy.remove(coly) ##### Only X columns
if len(colid) > 0:
cols_family_all['colid'] = colid
cols_family_all['colX'] = colXy
#### Cols group for model input ###########################################################
save(colXy, f'{path_pipeline_export}/colsX.pkl')
save(cols_family_all, f'{path_pipeline_export}/cols_family.pkl')
###### Return values #######################################################################
return dfXy, cols_family_all
def text_preprocess(path_train_X="",
path_train_y="",
path_pipeline_export="",
cols_group=None,
n_sample=5000,
preprocess_pars={},
filter_pars={},
path_features_store=None):
"""
:param path_train_X:
:param path_train_y:
:param path_pipeline_export:
:param cols_group:
:param n_sample:
:param preprocess_pars:
:param filter_pars:
:param path_features_store:
:return:
"""
from util_feature import (pd_colnum_tocat, pd_col_to_onehot,
pd_colcat_mapping, pd_colcat_toint,
pd_feature_generate_cross)
##### column names for feature generation ###############################################
log(cols_group)
coly = cols_group['coly'] # 'salary'
colid = cols_group['colid'] # "jobId"
colcat = cols_group[
'colcat'] # [ 'companyId', 'jobType', 'degree', 'major', 'industry' ]
colnum = cols_group['colnum'] # ['yearsExperience', 'milesFromMetropolis']
colcross_single = cols_group.get('colcross',
[]) ### List of single columns
coltext = cols_group.get('coltext', [])
coldate = cols_group.get('coldate', [])
colall = colnum + colcat + coltext + coldate
log(colall)
##### Load data ########################################################################
df = load_dataset(path_train_X, path_train_y, colid, n_sample=n_sample)
log("##### Coltext processing ###############################################################"
)
from utils import util_text, util_model
### Remoe common words #############################################
import json
import string
punctuations = string.punctuation
stopwords = json.load(open("stopwords_en.json"))["word"]
stopwords = [t for t in string.punctuation] + stopwords
stopwords = ["", " ", ",", ".", "-", "*", '€', "+", "/"] + stopwords
stopwords = list(set(stopwords))
stopwords.sort()
print(stopwords)
stopwords = set(stopwords)
def pipe_text(df, col, pars={}):
ntoken = pars['n_token']
df = df.fillna("")
dftext = df
log(dftext)
log(col)
list1 = []
list1.append(col)
# fromword = [ r"\b({w})\b".format(w=w) for w in fromword ]
# print(fromword)
for col_n in list1:
dftext[col_n] = dftext[col_n].fillna("")
dftext[col_n] = dftext[col_n].str.lower()
dftext[col_n] = dftext[col_n].apply(
lambda x: x.translate(string.punctuation))
dftext[col_n] = dftext[col_n].apply(
lambda x: x.translate(string.digits))
dftext[col_n] = dftext[col_n].apply(
lambda x: re.sub("[!@,#$+%*:()'-]", " ", x))
dftext[col_n] = dftext[col_n].apply(
lambda x: coltext_stopwords(x, stopwords=stopwords))
print(dftext.head(6))
sep = " "
"""
:param df:
:param coltext: text where word frequency should be extracted
:param nb_to_show:
:return:
"""
coltext_freq = df[col].apply(
lambda x: pd.value_counts(x.split(sep))).sum(axis=0).reset_index()
coltext_freq.columns = ["word", "freq"]
coltext_freq = coltext_freq.sort_values("freq", ascending=0)
log(coltext_freq)
word_tokeep = coltext_freq["word"].values[:ntoken]
word_tokeep = [t for t in word_tokeep if t not in stopwords]
dftext_tdidf_dict, word_tokeep_dict = util_text.pd_coltext_tdidf(
dftext,
coltext=col,
word_minfreq=1,
word_tokeep=word_tokeep,
return_val="dataframe,param")
log(word_tokeep_dict)
### Dimesnion reduction for Sparse Matrix
dftext_svd_list, svd_list = util_model.pd_dim_reduction(
dftext_tdidf_dict,
colname=None,
model_pretrain=None,
colprefix=col + "_svd",
method="svd",
dimpca=2,
return_val="dataframe,param")
return dftext_svd_list
pars = {'n_token': 100}
dftext1 = None
for coltext_i in coltext:
dftext_i = pipe_text(df[[coltext_i]], coltext_i, pars)
save_features(dftext_i, 'dftext_' + coltext_i, path_features_store)
dftext1 = pd.concat(
(dftext1, dftext_i)) if dftext1 is not None else dftext_i
print(dftext1.head(6))
dftext1.to_csv(r"" + path_features_store + "\dftext.csv", index=False)
##################################################################################################
##### Save pre-processor meta-parameters
os.makedirs(path_pipeline_export, exist_ok=True)
log(path_pipeline_export)
cols_family = {}
for t in ['coltext']:
tfile = f'{path_pipeline_export}/{t}.pkl'
log(tfile)
t_val = locals().get(t, None)
if t_val is not None:
save(t_val, tfile)
cols_family[t] = t_val
return dftext1, cols_family
def preprocess(path_train_X="", path_train_y="", path_pipeline_export="", cols_group=None, n_sample=5000,
preprocess_pars={}, filter_pars={}, path_features_store=None):
"""
:param path_train_X:
:param path_train_y:
:param path_pipeline_export:
:param cols_group:
:param n_sample:
:param preprocess_pars:
:param filter_pars:
:param path_features_store:
:return:
"""
from util_feature import (pd_colnum_tocat, pd_col_to_onehot, pd_colcat_mapping, pd_colcat_toint,
pd_feature_generate_cross)
##### column names for feature generation #####################################################
log(cols_group)
coly = cols_group['coly'] # 'salary'
colid = cols_group['colid'] # "jobId"
colcat = cols_group['colcat'] # [ 'companyId', 'jobType', 'degree', 'major', 'industry' ]
colnum = cols_group['colnum'] # ['yearsExperience', 'milesFromMetropolis']
colcross_single = cols_group.get('colcross', []) ### List of single columns
coltext = cols_group.get('coltext', [])
coldate = cols_group.get('coldate', [])
colall = colnum + colcat + coltext + coldate
log(colall)
#### Pipeline Execution
pipe_default = [ 'filter', 'label', 'dfnum_bin', 'dfnum_hot', 'dfcat_bin', 'dfcat_hot', 'dfcross_hot', ]
pipe_list = preprocess_pars.get('pipe_list', pipe_default)
pipe_list.append('dfdate')
pipe_list_pars = preprocess_pars.get('pipe_pars', [])
##### Load data ##############################################################################
df = load_dataset(path_train_X, path_train_y, colid, n_sample= n_sample)
##### Filtering / cleaning rows : #########################################################
if "filter" in pipe_list :
def isfloat(x):
try :
a= float(x)
return 1
except:
return 0
ymin, ymax = filter_pars.get('ymin', -9999999999.0), filter_pars.get('ymax', 999999999.0)
print(coly)
df['_isfloat'] = df[ coly ].apply(lambda x : isfloat(x))
print(df['_isfloat'])
df = df[ df['_isfloat'] > 0 ]
df = df[df[coly] > ymin]
df = df[df[coly] < ymax]
##### Label processing ####################################################################
y_norm_fun = None
if "label" in pipe_list :
# Target coly processing, Normalization process , customize by model
log("y_norm_fun preprocess_pars")
y_norm_fun = preprocess_pars.get('y_norm_fun', None)
if y_norm_fun is not None:
df[coly] = df[coly].apply(lambda x: y_norm_fun(x))
save(y_norm_fun, f'{path_pipeline_export}/y_norm.pkl' )
save_features(df[coly], 'dfy', path_features_store)
########### colnum procesing #############################################################
for x in colnum:
print('bam',x)
df[x] = df[x].astype("float")
log(df[colall].dtypes)
if "dfnum" in pipe_list :
pass
if "dfnum_norm" in pipe_list :
log("### colnum normalize ###############################################################")
from util_feature import pd_colnum_normalize
pars = { 'pipe_list': [ {'name': 'fillna', 'naval' : 0.0 }, {'name': 'minmax'} ]}
dfnum_norm, colnum_norm = pd_colnum_normalize(df, colname=colnum, pars=pars, suffix = "_norm",
return_val="dataframe,param")
log(colnum_norm)
save_features(dfnum_norm, 'dfnum_norm', path_features_store)
if "dfnum_bin" in pipe_list :
log("### colnum Map numerics to Category bin ###########################################")
dfnum_bin, colnum_binmap = pd_colnum_tocat(df, colname=colnum, colexclude=None, colbinmap=None,
bins=10, suffix="_bin", method="uniform",
return_val="dataframe,param")
log(colnum_binmap)
### Renaming colunm_bin with suffix
colnum_bin = [x + "_bin" for x in list(colnum_binmap.keys())]
log(colnum_bin)
save_features(dfnum_bin, 'dfnum_binmap', path_features_store)
if "dfnum_hot" in pipe_list and "dfnum_bin" in pipe_list :
log("### colnum bin to One Hot")
dfnum_hot, colnum_onehot = pd_col_to_onehot(dfnum_bin[colnum_bin], colname=colnum_bin,
colonehot=None, return_val="dataframe,param")
log(colnum_onehot)
save_features(dfnum_hot, 'dfnum_onehot', path_features_store)
##### Colcat processing ################################################################
colcat_map = pd_colcat_mapping(df, colcat)
log(df[colcat].dtypes, colcat_map)
if "dfcat_hot" in pipe_list :
log("#### colcat to onehot")
dfcat_hot, colcat_onehot = pd_col_to_onehot(df[colcat], colname=colcat,
colonehot=None, return_val="dataframe,param")
log(dfcat_hot[colcat_onehot].head(5))
save_features(dfcat_hot, 'dfcat_onehot', path_features_store)
if "dfcat_bin" in pipe_list :
log("#### Colcat to integer encoding ")
dfcat_bin, colcat_bin_map = pd_colcat_toint(df[colcat], colname=colcat,
colcat_map=None, suffix="_int")
colcat_bin = list(dfcat_bin.columns)
save_features(dfcat_bin, 'dfcat_bin', path_features_store)
if "dfcross_hot" in pipe_list :
log("##### Cross Features From OneHot Features ######################################")
try :
df_onehot = dfcat_hot.join(dfnum_hot, on=colid, how='left')
except :
df_onehot = copy.deepcopy(dfcat_hot)
colcross_single_onehot_select = []
for t in list(df_onehot) :
for c1 in colcross_single :
if c1 in t :
colcross_single_onehot_select.append(t)
df_onehot = df_onehot[colcross_single_onehot_select ]
dfcross_hot, colcross_pair = pd_feature_generate_cross(df_onehot, colcross_single_onehot_select,
pct_threshold=0.02, m_combination=2)
log(dfcross_hot.head(2).T)
colcross_pair_onehot = list(dfcross_hot.columns)
save_features(dfcross_hot, 'dfcross_onehot', path_features_store)
del df_onehot ,colcross_pair_onehot
if "dftext" in pipe_list :
log("##### Coltext processing ###############################################################")
stopwords = nlp_get_stopwords()
pars = {'n_token' : 100 , 'stopwords': stopwords}
dftext = None
for coltext_i in coltext :
##### Run the text processor on each column text #############################
dftext_i = pipe_text( df[[coltext_i ]], coltext_i, pars )
dftext = pd.concat((dftext, dftext_i), axis=1) if dftext is not None else dftext_i
save_features(dftext_i, 'dftext_' + coltext_i, path_features_store)
log(dftext.head(6))
save_features(dftext, 'dftext', path_features_store)
if "dfdate" in pipe_list :
log("##### Coldate processing #############################################################")
from utils import util_date
dfdate = None
for coldate_i in coldate :
dfdate_i = util_date.pd_datestring_split( df[[coldate_i]] , coldate_i, fmt="auto", return_val= "split" )
dfdate = pd.concat((dfdate, dfdate_i), axis=1) if dfdate is not None else dfdate_i
save_features(dfdate_i, 'dfdate_' + coldate_i, path_features_store)
save_features(dfdate, 'dfdate', path_features_store)
print('spoo',dfdate)
###################################################################################
# ###############
##### Save pre-processor meta-parameters
os.makedirs(path_pipeline_export, exist_ok=True)
log(path_pipeline_export)
cols_family = {}
for t in ['colid',
"colnum", "colnum_bin", "colnum_onehot", "colnum_binmap", #### Colnum columns
"colcat", "colcat_bin", "colcat_onehot", "colcat_bin_map", #### colcat columns
'colcross_single_onehot_select', "colcross_pair_onehot", 'colcross_pair', #### colcross columns
'coldate',
'coltext',
"coly", "y_norm_fun"
]:
tfile = f'{path_pipeline_export}/{t}.pkl'
log(tfile)
t_val = locals().get(t, None)
if t_val is not None :
save(t_val, tfile)
cols_family[t] = t_val
###### Merge AlL #############################################################################
dfXy = df[colnum + colcat + [coly] ]
print('localTT',dfXy)
for t in [ 'dfnum_bin', 'dfnum_hot', 'dfcat_bin', 'dfcat_hot', 'dfcross_hot',
'dfdate', 'dftext' ] :
if t in locals() :
print('localT', t, locals()[t])
dfXy = pd.concat((dfXy, locals()[t] ), axis=1)
save_features(dfXy, 'dfX', path_features_store)
colXy = list(dfXy.columns)
colXy.remove(coly) ##### Only X columns
cols_family['colX'] = colXy
save(colXy, f'{path_pipeline_export}/colsX.pkl' )
save(cols_family, f'{path_pipeline_export}/cols_family.pkl' )
###### Return values #########################################################################
return dfXy, cols_family
def run_predict(config_name,
config_path,
n_sample=-1,
path_data=None,
path_output=None,
pars={},
model_dict=None):
log("#### Run predict ###############################################################"
)
model_dict = model_dict_load(model_dict,
config_path,
config_name,
verbose=True)
model_class = model_dict['model_pars']['model_class']
m = model_dict['global_pars']
path_data = m['path_pred_data'] if path_data is None else path_data
path_pipeline = m['path_pred_pipeline'] # path_output + "/pipeline/" )
path_model = m['path_pred_model']
path_output = m['path_pred_output'] if path_output is None else path_output
log(path_data, path_model, path_output)
pars = {
'cols_group': model_dict['data_pars']['cols_input_type'],
'pipe_list': model_dict['model_pars']['pre_process_pars']['pipe_list']
}
log("#### Run preprocess ###########################################################"
)
from run_preprocess import preprocess_inference as preprocess
colid = load(f'{path_pipeline}/colid.pkl')
df = load_dataset(path_data,
path_data_y=None,
colid=colid,
n_sample=n_sample)
dfX, cols = preprocess(df, path_pipeline, preprocess_pars=pars)
coly = cols["coly"]
log("#### Extract column names #########################################################"
)
### Actual column names for Model Input : label y and Input X (colnum , colcat), remove duplicate names
### [ 'colcat', 'colnum'
model_dict['data_pars']['coly'] = cols['coly']
model_dict['data_pars']['cols_model'] = list(
set(
sum([
cols[colgroup]
for colgroup in model_dict['data_pars']['cols_model_group']
], [])))
#### Flatten Col Group by column type : Sparse, continuous, .... (ie Neural Network feed Input, remove duplicate names
## 'coldense' = [ 'colnum' ] 'colsparse' = ['colcat' ]
model_dict['data_pars']['cols_model_type2'] = {}
for colg, colg_list in model_dict['data_pars'].get('cols_model_type',
{}).items():
model_dict['data_pars']['cols_model_type2'][colg] = list(
set(sum([cols[colgroup] for colgroup in colg_list], [])))
log("############ Prediction ##########################################################"
)
ypred, yproba = predict(model_class, path_model, dfX, cols, model_dict)
post_process_fun = model_dict['model_pars']['post_process_fun']
df[coly + "_pred"] = ypred
df[coly + "_pred"] = df[coly +
'_pred'].apply(lambda x: post_process_fun(x))
if yproba is not None:
df[coly + "_pred_proba"] = yproba
log("############ Saving prediction ###################################################"
)
log(ypred.shape, path_output)
os.makedirs(path_output, exist_ok=True)
df.to_csv(f"{path_output}/prediction.csv")
log(df.head(8))
log("########### Export Specific ######################################################"
)
df[cols["coly"]] = ypred
df[[cols["coly"]]].to_csv(f"{path_output}/pred_only.csv")
def run_transform(config_name,
config_path,
n_sample=1,
path_data=None,
path_output=None,
pars={},
model_dict=None,
return_mode=""):
log("##### Run transform ###############################################################"
)
model_dict = model_dict_load(model_dict,
config_path,
config_name,
verbose=True)
model_class = model_dict['model_pars']['model_class']
m = model_dict['global_pars']
path_data = m['path_pred_data'] if path_data is None else path_data
path_pipeline = m['path_pred_pipeline'] # path_output + "/pipeline/" )
path_model = m['path_pred_model']
model_file = m.get('model_file', "") ### New
path_output = m['path_pred_output'] if path_output is None else path_output
log(path_data, path_model, path_output)
pars = {
'cols_group': model_dict['data_pars']['cols_input_type'],
'pipe_list': model_dict['model_pars']['pre_process_pars']['pipe_list']
}
log("##### Load Preprocess ############################################################"
)
from run_preprocess import preprocess_inference as preprocess
colid = load(f'{path_pipeline}/colid.pkl')
if model_class in SUPERVISED_MODELS:
path_pred_X = m.get('path_pred_X', path_data + "/features.zip") #.zip
path_pred_y = m.get('path_pred_y', path_data + "/target.zip") #.zip
df = load_dataset(path_pred_X, path_pred_y, colid, n_sample=n_sample)
else:
df = load_dataset(path_data, None, colid, n_sample=n_sample)
dfX, cols = preprocess(df, path_pipeline, preprocess_pars=pars)
coly = cols["coly"]
log("#### Extract column names #######################################################"
)
### Actual column names for Model Input : label y and Input X (colnum , colcat), remove duplicate names
model_dict['data_pars']['coly'] = cols['coly']
model_dict['data_pars']['cols_model'] = list(
set(
sum([
cols[colgroup]
for colgroup in model_dict['data_pars']['cols_model_group']
], [])))
#### Col Group by column type : Sparse, continuous, .... (ie Neural Network feed Input, remove duplicate names
#### 'coldense' = [ 'colnum' ] 'colsparse' = ['colcat' ]
model_dict['data_pars']['cols_model_type2'] = {}
for colg, colg_list in model_dict['data_pars'].get('cols_model_type',
{}).items():
model_dict['data_pars']['cols_model_type2'][colg] = list(
set(sum([cols[colgroup] for colgroup in colg_list], [])))
log("############ Task Inference ###################################################"
)
task_type = model_dict['compute_pars'].get('task_inference', 'transform')
if model_class in SUPERVISED_MODELS:
dfXy = transform(
model_file,
path_model,
(dfX[[c for c in dfX.columns if c not in coly]], df[coly]),
model_dict,
task_type=task_type)
else:
dfXy = transform(model_file,
path_model,
dfX,
model_dict,
task_type=task_type)
post_process_fun = model_dict['model_pars']['post_process_fun']
if return_mode == 'dict':
return {'dfXy': dfXy}
else:
log("#### Export ##################################################################"
)
path_check_out = m.get('path_check_out', path_output + "/check/")
os.makedirs(path_check_out, exist_ok=True)
dfX.to_parquet(path_check_out +
"/dfX.parquet") # train input data generate parquet
log(
"######### Finish #############################################################",
)