py2ls 0.2.2__py3-none-any.whl → 0.2.3__py3-none-any.whl

py2ls/data/usages_pd.json

@@ -0,0 +1,56 @@
+{
+    "pd.read_pickle": "pd.read_pickle(filepath_or_buffer,compression='infer',storage_options=None)",
+    "df.to_pickle": "df.to_pickle(path,*,compression='infer',protocol=5,storage_options=None)",
+    "pd.read_table": "pd.read_table(filepath_or_buffer,*,sep=<no_default>,delimiter=None,header='infer',names=<no_default>,index_col=None,usecols=None,dtype=None,engine=None,converters=None,true_values=None,false_values=None,skipinitialspace=False,skiprows=None,skipfooter=0,nrows=None,na_values=None,keep_default_na=True,na_filter=True,verbose=<no_default>,skip_blank_lines=True,parse_dates=False,infer_datetime_format=<no_default>,keep_date_col=<no_default>,date_parser=<no_default>,date_format=None,dayfirst=False,cache_dates=True,iterator=False,chunksize=None,compression='infer',thousands=None,decimal='.',lineterminator=None,quotechar='\"',quoting=0,doublequote=True,escapechar=None,comment=None,encoding=None,encoding_errors='strict',dialect=None,on_bad_lines='error',delim_whitespace=<no_default>,low_memory=True,memory_map=False,float_precision=None,storage_options=None,dtype_backend=<no_default>)",
+    "pd.read_csv": "pd.read_csv(filepath_or_buffer,*,sep=<no_default>,delimiter=None,header='infer',names=<no_default>,index_col=None,usecols=None,dtype=None,engine=None,converters=None,true_values=None,false_values=None,skipinitialspace=False,skiprows=None,skipfooter=0,nrows=None,na_values=None,keep_default_na=True,na_filter=True,verbose=<no_default>,skip_blank_lines=True,parse_dates=None,infer_datetime_format=<no_default>,keep_date_col=<no_default>,date_parser=<no_default>,date_format=None,dayfirst=False,cache_dates=True,iterator=False,chunksize=None,compression='infer',thousands=None,decimal='.',lineterminator=None,quotechar='\"',quoting=0,doublequote=True,escapechar=None,comment=None,encoding=None,encoding_errors='strict',dialect=None,on_bad_lines='error',delim_whitespace=<no_default>,low_memory=True,memory_map=False,float_precision=None,storage_options=None,dtype_backend=<no_default>)",
+    "df.to_csv": "df.to_csv(path_or_buf=None,*,sep=',',na_rep='',float_format=None,columns=None,header=True,index=True,index_label=None,mode='w',encoding=None,compression='infer',quoting=None,quotechar='\"',lineterminator=None,chunksize=None,date_format=None,doublequote=True,escapechar=None,decimal='.',errors='strict',storage_options=None)",
+    "pd.read_fwf": "pd.read_fwf(filepath_or_buffer,*,colspecs='infer',widths=None,infer_nrows=100,dtype_backend=<no_default>,iterator=False,chunksize=None,**kwds)",
+    "pd.read_clipboard": "pd.read_clipboard(sep='\\\\s+',dtype_backend=<no_default>,**kwargs)",
+    "pd.read_excel": "pd.read_excel(io,sheet_name=0,*,header=0,names=None,index_col=None,usecols=None,dtype=None,engine=None,converters=None,true_values=None,false_values=None,skiprows=None,nrows=None,na_values=None,keep_default_na=True,na_filter=True,verbose=False,parse_dates=False,date_parser=<no_default>,date_format=None,thousands=None,decimal='.',comment=None,skipfooter=0,storage_options=None,dtype_backend=<no_default>,engine_kwargs=None)",
+    "df.to_excel": "df.to_excel(excel_writer,*,sheet_name='Sheet1',na_rep='',float_format=None,columns=None,header=True,index=True,index_label=None,startrow=0,startcol=0,engine=None,merge_cells=True,inf_rep='inf',freeze_panes=None,storage_options=None,engine_kwargs=None)",
+    "classpandas.ExcelFile": "classpandas.ExcelFile(path_or_buffer,engine=None,storage_options=None,engine_kwargs=None)",
+    "propertyExcelFile.book": "propertyExcelFile.book",
+    "propertyExcelFile.sheet_names": "propertyExcelFile.sheet_names",
+    "ExcelFile.parse": "ExcelFile.parse(sheet_name=0,header=0,names=None,index_col=None,usecols=None,converters=None,true_values=None,false_values=None,skiprows=None,nrows=None,na_values=None,parse_dates=False,date_parser=<no_default>,date_format=None,thousands=None,comment=None,skipfooter=0,dtype_backend=<no_default>,**kwds)",
+    "Styler.to_excel": "Styler.to_excel(excel_writer,sheet_name='Sheet1',na_rep='',float_format=None,columns=None,header=True,index=True,index_label=None,startrow=0,startcol=0,engine=None,merge_cells=True,encoding=None,inf_rep='inf',verbose=True,freeze_panes=None,storage_options=None)",
+    "classpandas.ExcelWriter": "classpandas.ExcelWriter(path,engine=None,date_format=None,datetime_format=None,mode='w',storage_options=None,if_sheet_exists=None,engine_kwargs=None)",
+    "pd.read_json": "pd.read_json(path_or_buf,*,orient=None,typ='frame',dtype=None,convert_axes=None,convert_dates=True,keep_default_dates=True,precise_float=False,date_unit=None,encoding=None,encoding_errors='strict',lines=False,chunksize=None,compression='infer',nrows=None,storage_options=None,dtype_backend=<no_default>,engine='ujson')",
+    "pd.json_normalize": "pd.json_normalize(data,record_path=None,meta=None,meta_prefix=None,record_prefix=None,errors='raise',sep='.',max_level=None)",
+    "df.to_json": "df.to_json(path_or_buf=None,*,orient=None,date_format=None,double_precision=10,force_ascii=True,date_unit='ms',default_handler=None,lines=False,compression='infer',index=None,indent=None,storage_options=None,mode='w')",
+    "pd.io.json.build_table_schema": "pd.io.json.build_table_schema(data,index=True,primary_key=None,version=True)",
+    "pd.read_html": "pd.read_html(io,*,match='.+',flavor=None,header=None,index_col=None,skiprows=None,attrs=None,parse_dates=False,thousands=',',encoding=None,decimal='.',converters=None,na_values=None,keep_default_na=True,displayed_only=True,extract_links=None,dtype_backend=<no_default>,storage_options=None)",
+    "df.to_html": "df.to_html(buf=None,*,columns=None,col_space=None,header=True,index=True,na_rep='NaN',formatters=None,float_format=None,sparsify=None,index_names=True,justify=None,max_rows=None,max_cols=None,show_dimensions=False,decimal='.',bold_rows=True,classes=None,escape=True,notebook=False,border=None,table_id=None,render_links=False,encoding=None)",
+    "Styler.to_html": "Styler.to_html(buf=None,*,table_uuid=None,table_attributes=None,sparse_index=None,sparse_columns=None,bold_headers=False,caption=None,max_rows=None,max_columns=None,encoding=None,doctype_html=False,exclude_styles=False,**kwargs)",
+    "pd.read_xml": "pd.read_xml(path_or_buffer,*,xpath='./*',namespaces=None,elems_only=False,attrs_only=False,names=None,dtype=None,converters=None,parse_dates=None,encoding='utf-8',parser='lxml',stylesheet=None,iterparse=None,compression='infer',storage_options=None,dtype_backend=<no_default>)",
+    "df.to_xml": "df.to_xml(path_or_buffer=None,*,index=True,root_name='data',row_name='row',na_rep=None,attr_cols=None,elem_cols=None,namespaces=None,prefix=None,encoding='utf-8',xml_declaration=True,pretty_print=True,parser='lxml',stylesheet=None,compression='infer',storage_options=None)",
+    "df.to_latex": "df.to_latex(buf=None,*,columns=None,header=True,index=True,na_rep='NaN',formatters=None,float_format=None,sparsify=None,index_names=True,bold_rows=False,column_format=None,longtable=None,escape=None,encoding=None,decimal='.',multicolumn=None,multicolumn_format=None,multirow=None,caption=None,label=None,position=None)",
+    "Styler.to_latex": "Styler.to_latex(buf=None,*,column_format=None,position=None,position_float=None,hrules=None,clines=None,label=None,caption=None,sparse_index=None,sparse_columns=None,multirow_align=None,multicol_align=None,siunitx=False,environment=None,encoding=None,convert_css=False)",
+    "pd.read_hdf": "pd.read_hdf(path_or_buf,key=None,mode='r',errors='strict',where=None,start=None,stop=None,columns=None,iterator=False,chunksize=None,**kwargs)",
+    "HDFStore.put": "HDFStore.put(key,value,format=None,index=True,append=False,complib=None,complevel=None,min_itemsize=None,nan_rep=None,data_columns=None,encoding=None,errors='strict',track_times=True,dropna=False)",
+    "HDFStore.append": "HDFStore.append(key,value,format=None,axes=None,index=True,append=True,complib=None,complevel=None,columns=None,min_itemsize=None,nan_rep=None,chunksize=None,expectedrows=None,dropna=None,data_columns=None,encoding=None,errors='strict')",
+    "HDFStore.get": "HDFStore.get(key)",
+    "HDFStore.select": "HDFStore.select(key,where=None,start=None,stop=None,columns=None,iterator=False,chunksize=None,auto_close=False)",
+    "HDFStore.info": "HDFStore.info()",
+    "HDFStore.keys": "HDFStore.keys(include='pandas')",
+    "HDFStore.groups": "HDFStore.groups()",
+    "HDFStore.walk": "HDFStore.walk(where='/')",
+    "pd.read_feather": "pd.read_feather(path,columns=None,use_threads=True,storage_options=None,dtype_backend=<no_default>)",
+    "df.to_feather": "df.to_feather(path,**kwargs)",
+    "pd.read_parquet": "pd.read_parquet(path,engine='auto',columns=None,storage_options=None,use_nullable_dtypes=<no_default>,dtype_backend=<no_default>,filesystem=None,filters=None,**kwargs)",
+    "df.to_parquet": "df.to_parquet(path=None,*,engine='auto',compression='snappy',index=None,partition_cols=None,storage_options=None,**kwargs)",
+    "pd.read_orc": "pd.read_orc(path,columns=None,dtype_backend=<no_default>,filesystem=None,**kwargs)",
+    "df.to_orc": "df.to_orc(path=None,*,engine='pyarrow',index=None,engine_kwargs=None)",
+    "pd.read_sas": "pd.read_sas(filepath_or_buffer,*,format=None,index=None,encoding=None,chunksize=None,iterator=False,compression='infer')",
+    "pd.read_spss": "pd.read_spss(path,usecols=None,convert_categoricals=True,dtype_backend=<no_default>)",
+    "pd.read_sql_table": "pd.read_sql_table(table_name,con,schema=None,index_col=None,coerce_float=True,parse_dates=None,columns=None,chunksize=None,dtype_backend=<no_default>)",
+    "pd.read_sql_query": "pd.read_sql_query(sql,con,index_col=None,coerce_float=True,params=None,parse_dates=None,chunksize=None,dtype=None,dtype_backend=<no_default>)",
+    "pd.read_sql": "pd.read_sql(sql,con,index_col=None,coerce_float=True,params=None,parse_dates=None,columns=None,chunksize=None,dtype_backend=<no_default>,dtype=None)",
+    "df.to_sql": "df.to_sql(name,con,*,schema=None,if_exists='fail',index=True,index_label=None,chunksize=None,dtype=None,method=None)",
+    "pd.read_gbq": "pd.read_gbq(query,project_id=None,index_col=None,col_order=None,reauth=False,auth_local_webserver=True,dialect=None,location=None,configuration=None,credentials=None,use_bqstorage_api=None,max_results=None,progress_bar_type=None)",
+    "pd.read_stata": "pd.read_stata(filepath_or_buffer,*,convert_dates=True,convert_categoricals=True,index_col=None,convert_missing=False,preserve_dtypes=True,columns=None,order_categoricals=True,chunksize=None,iterator=False,compression='infer',storage_options=None)",
+    "df.to_stata": "df.to_stata(path,*,convert_dates=None,write_index=True,byteorder=None,time_stamp=None,data_label=None,variable_labels=None,version=114,convert_strl=None,compression='infer',storage_options=None,value_labels=None)",
+    "propertyStataReader.data_label": "propertyStataReader.data_label",
+    "StataReader.value_labels": "StataReader.value_labels()",
+    "StataReader.variable_labels": "StataReader.variable_labels()",
+    "StataWriter.write_file": "StataWriter.write_file()"
+}

py2ls/ips.py

@@ -1551,10 +1551,14 @@ def fload(fpath, kind=None, **kwargs):
             content = file.read()
         return content
 
-    def load_json(fpath):
-        with open(fpath, "r") as file:
-            content = json.load(file)
-        return content
+    def load_json(fpath, **kwargs):
+        output=kwargs.pop("output","json")
+        if output=='json': 
+            with open(fpath, "r") as file:
+                content = json.load(file)
+            return content
+        else:
+            return pd.read_json(fpath,**kwargs)
 
     def load_yaml(fpath):
         with open(fpath, "r") as file:
@@ -1616,6 +1620,11 @@ def fload(fpath, kind=None, **kwargs):
         comment = kwargs.get("comment", None)
         kwargs.pop("comment", None)
 
+        fmt=kwargs.pop("fmt",False)
+        if verbose:
+            print_pd_usage("read_csv", verbose=verbose)
+            return
+        
         if comment is None:
             comment = get_comment(
                 fpath, comment=None, encoding="utf-8", lines_to_check=5
@@ -1743,7 +1752,9 @@ def fload(fpath, kind=None, **kwargs):
 
     def load_xlsx(fpath, **kwargs):
         engine = kwargs.get("engine", "openpyxl")
-        kwargs.pop("engine", None)
+        verbose=kwargs.pop("verbose",False)
+        if verbose:
+            print_pd_usage("read_excel", verbose=verbose)
         df = pd.read_excel(fpath, engine=engine, **kwargs)
         return df
 
@@ -1813,7 +1824,6 @@ def fload(fpath, kind=None, **kwargs):
     if kind is None:
         _, kind = os.path.splitext(fpath)
         kind = kind.lower()
-
     kind = kind.lstrip(".").lower()
     img_types = [
         "bmp",
@@ -4291,8 +4301,6 @@ def preview(var):
 # preview(pd.DataFrame({"Name": ["Alice", "Bob"], "Age": [25, 30]}))
 # preview({"key": "value", "numbers": [1, 2, 3]})
 
-
-# ! DataFrame
 def df_as_type(
     df: pd.DataFrame,
     columns: Optional[Union[str, List[str]]] = None,
@@ -4301,6 +4309,18 @@ def df_as_type(
     inplace: bool = True,
     errors: str = "coerce",  # Can be "ignore", "raise", or "coerce"
     **kwargs,
+):
+    return df_astype(df=df,columns=columns,astype=astype,format=format,inplace=inplace,errors=errors,**kwargs)
+
+# ! DataFrame
+def df_astype(
+    df: pd.DataFrame,
+    columns: Optional[Union[str, List[str]]] = None,
+    astype: str = "datetime",
+    fmt: Optional[str] = None,
+    inplace: bool = True,
+    errors: str = "coerce",  # Can be "ignore", "raise", or "coerce"
+    **kwargs,
 ) -> Optional[pd.DataFrame]:
     """
     Convert specified columns of a DataFrame to a specified type (e.g., datetime, float, int, numeric, timedelta).
@@ -4310,7 +4330,7 @@ def df_as_type(
     - df: DataFrame containing the columns to convert.
     - columns: Either a single column name, a list of column names, or None to convert all columns.
     - astype: The target type to convert the columns to ('datetime', 'float', 'int', 'numeric', 'timedelta', etc.).
-    - format: Optional; format to specify the datetime format (only relevant for 'datetime' conversion).
+    - fmt: Optional; format to specify the datetime format (only relevant for 'datetime' conversion).
     - inplace: Whether to modify the DataFrame in place or return a new one. Defaults to False.
     - errors: Can be "ignore", "raise", or "coerce"
     - **kwargs: Additional keyword arguments to pass to the conversion function (e.g., errors='ignore' for pd.to_datetime or pd.to_numeric).
@@ -4390,7 +4410,7 @@ def df_as_type(
                 # convert it as type: datetime
                 if isinstance(column, int):
                     df.iloc[:, column] = pd.to_datetime(
-                        df.iloc[:, column], format=format, errors=errors, **kwargs
+                        df.iloc[:, column], format=fmt, errors=errors, **kwargs
                     )
                     # further convert:
                     if astype == "time":
@@ -4412,9 +4432,9 @@ def df_as_type(
                 else:
                     df[column] = (
                         pd.to_datetime(
-                            df[column], format=format, errors=errors, **kwargs
+                            df[column], format=fmt, errors=errors, **kwargs
                         )
-                        if format
+                        if fmt
                         else pd.to_datetime(df[column], errors=errors, **kwargs)
                     )
                     # further convert:
@@ -5227,3 +5247,20 @@ def evaluate_cluster(
             metrics["V-Measure"] = np.nan
 
     return metrics
+
+
+def print_pd_usage(
+    func_name="excel",
+    verbose=True,
+    dir_json="/Users/macjianfeng/Dropbox/github/python/py2ls/py2ls/data/usages_pd.json",
+):
+    default_settings = fload(dir_json, output='json')
+    valid_kinds = list(default_settings.keys())
+    kind = strcmp(func_name, valid_kinds)[0]
+    usage=default_settings[kind]
+    if verbose:
+        for i, i_ in enumerate(ssplit(usage, by=",")):
+            i_ = i_.replace("=", "\t= ") + ","
+            print(i_) if i == 0 else print("\t", i_)
+    else:
+        print(usage)

py2ls/plot.py

@@ -20,71 +20,6 @@ from .netfinder import get_soup, fetch
 logging.getLogger("fontTools").setLevel(logging.WARNING)
 
 
-def update_sns_usages(
-    url="https://seaborn.pydata.org/generated/seaborn.swarmplot.html",
-    dir_save=None,
-):
-    """
-    Fetches usage examples of various Seaborn plotting functions from the Seaborn documentation website.
-    It filters the relevant plot-related links, extracts usage examples, and saves them in a JSON file.
-
-    Parameters:
-    - url (str): URL of the Seaborn page to start extracting plot usages (default is swarmplot page).
-    - dir_save (str): Directory where the JSON file containing usages will be saved (default is a local path).
-
-    Saves:
-    - A JSON file named 'usages_sns.json' containing plotting function names and their usage descriptions.
-
-    Returns:
-    - None
-    """
-
-    # extract each usage from its url
-    def get_usage(url):
-        sp = get_soup(url, driver="se")
-        # preview(sp)
-        return fetch(sp, where="dt")[0]
-
-    if dir_save is None:
-        if "mac" in get_os():
-            dir_save = "/Users/macjianfeng/Dropbox/github/python/py2ls/py2ls/data/"
-        else:
-            dir_save = "Z:\\Jianfeng\\temp\\"
-    sp = get_soup(url, driver="se")
-    links_all = fetch(sp, where="a", get="href", class_="reference internal")
-    filtered_links = unique(
-        [
-            i
-            for i in links_all
-            if not any(
-                [
-                    i.startswith(cond)
-                    for cond in [
-                        "seaborn.JointGrid",
-                        "seaborn.PairGrid",
-                        "seaborn.objects",
-                    ]
-                ]
-                + ["plot" not in i]
-            )
-        ]
-    )
-    links = ["https://seaborn.pydata.org/generated/" + i for i in filtered_links]
-
-    usages = [get_usage(i) for i in links]
-    dict_usage = {}
-    for usage in usages:
-        dict_usage.update(
-            {ssplit(usage, by="(")[0].replace("seaborn.", ""): usage[:-1]}
-        )
-    # save to local
-    dir_save += "/" if not dir_save.endswith("/") else ""
-    fsave(
-        dir_save + "usages_sns.json",
-        dict_usage,
-    )
-
-
 def heatmap(
     data,
     ax=None,
@@ -2920,17 +2855,17 @@ def plot_xy(
         # (1) return FcetGrid
         if k == "jointplot":
             kws_joint = kwargs.pop("kws_joint", kwargs)
-            g = sns.jointplot(data=data, x=x, y=y, hue=hue, **kws_joint)
+            g = sns.jointplot(data=data, x=x, y=y, **kws_joint)
         elif k == "lmplot":
             kws_lm = kwargs.pop("kws_lm", kwargs)
-            g = sns.lmplot(data=data, x=x, y=y, hue=hue, **kws_lm)
+            g = sns.lmplot(data=data, x=x, y=y, **kws_lm)
         elif k == "catplot_sns":
             kws_cat = kwargs.pop("kws_cat", kwargs)
-            g = sns.catplot(data=data, x=x, y=y, hue=hue, **kws_cat)
+            g = sns.catplot(data=data, x=x, y=y, **kws_cat)
         elif k == "displot":
             kws_dis = kwargs.pop("kws_dis", kwargs)
             # displot creates a new figure and returns a FacetGrid
-            g = sns.displot(data=data, x=x, hue=hue, **kws_dis)
+            g = sns.displot(data=data, x=x, **kws_dis)
 
         # (2) return axis
         if ax is None:
@@ -2939,6 +2874,9 @@ def plot_xy(
         if k == "catplot":
             kws_cat = kwargs.pop("kws_cat", kwargs)
             g = catplot(data=data, x=x, y=y, ax=ax, **kws_cat)
+        elif k == "stdshade":
+            kws_stdshade = kwargs.pop("kws_stdshade", kwargs)
+            ax = stdshade(ax=ax, **kwargs)
         elif k == "scatterplot":
             kws_scatter = kwargs.pop("kws_scatter", kwargs)
             palette = kws_scatter.pop(
@@ -2964,41 +2902,41 @@ def plot_xy(
             )
         elif k == "histplot":
             kws_hist = kwargs.pop("kws_hist", kwargs)
-            ax = sns.histplot(data=data, x=x, hue=hue, ax=ax, **kws_hist)
+            ax = sns.histplot(data=data, x=x, ax=ax, **kws_hist)
         elif k == "kdeplot":
             kws_kde = kwargs.pop("kws_kde", kwargs)
-            ax = sns.kdeplot(data=data, x=x, hue=hue, ax=ax, **kws_kde)
+            ax = sns.kdeplot(data=data, x=x, ax=ax, **kws_kde)
         elif k == "ecdfplot":
             kws_ecdf = kwargs.pop("kws_ecdf", kwargs)
-            ax = sns.ecdfplot(data=data, x=x, hue=hue, ax=ax, **kws_ecdf)
+            ax = sns.ecdfplot(data=data, x=x, ax=ax, **kws_ecdf)
         elif k == "rugplot":
             kws_rug = kwargs.pop("kws_rug", kwargs)
             print(kws_rug)
-            ax = sns.rugplot(data=data, x=x, hue=hue, ax=ax, **kws_rug)
+            ax = sns.rugplot(data=data, x=x, ax=ax, **kws_rug)
         elif k == "stripplot":
             kws_strip = kwargs.pop("kws_strip", kwargs)
-            ax = sns.stripplot(data=data, x=x, y=y, hue=hue, ax=ax, **kws_strip)
+            ax = sns.stripplot(data=data, x=x, y=y, ax=ax, **kws_strip)
         elif k == "swarmplot":
             kws_swarm = kwargs.pop("kws_swarm", kwargs)
-            ax = sns.swarmplot(data=data, x=x, y=y, hue=hue, ax=ax, **kws_swarm)
+            ax = sns.swarmplot(data=data, x=x, y=y, ax=ax, **kws_swarm)
         elif k == "boxplot":
             kws_box = kwargs.pop("kws_box", kwargs)
-            ax = sns.boxplot(data=data, x=x, y=y, hue=hue, ax=ax, **kws_box)
+            ax = sns.boxplot(data=data, x=x, y=y, ax=ax, **kws_box)
         elif k == "violinplot":
             kws_violin = kwargs.pop("kws_violin", kwargs)
-            ax = sns.violinplot(data=data, x=x, y=y, hue=hue, ax=ax, **kws_violin)
+            ax = sns.violinplot(data=data, x=x, y=y, ax=ax, **kws_violin)
         elif k == "boxenplot":
             kws_boxen = kwargs.pop("kws_boxen", kwargs)
-            ax = sns.boxenplot(data=data, x=x, y=y, hue=hue, ax=ax, **kws_boxen)
+            ax = sns.boxenplot(data=data, x=x, y=y, ax=ax, **kws_boxen)
         elif k == "pointplot":
             kws_point = kwargs.pop("kws_point", kwargs)
-            ax = sns.pointplot(data=data, x=x, y=y, hue=hue, ax=ax, **kws_point)
+            ax = sns.pointplot(data=data, x=x, y=y, ax=ax, **kws_point)
         elif k == "barplot":
             kws_bar = kwargs.pop("kws_bar", kwargs)
-            ax = sns.barplot(data=data, x=x, y=y, hue=hue, ax=ax, **kws_bar)
+            ax = sns.barplot(data=data, x=x, y=y, ax=ax, **kws_bar)
         elif k == "countplot":
             kws_count = kwargs.pop("kws_count", kwargs)
-            ax = sns.countplot(data=data, x=x, hue=hue, ax=ax, **kws_count)
+            ax = sns.countplot(data=data, x=x, ax=ax, **kws_count)
         elif k == "regplot":
             kws_reg = kwargs.pop("kws_reg", kwargs)
             ax = sns.regplot(data=data, x=x, y=y, ax=ax, **kws_reg)
@@ -3007,7 +2945,7 @@ def plot_xy(
             ax = sns.residplot(data=data, x=x, y=y, lowess=True, ax=ax, **kws_resid)
         elif k == "lineplot":
             kws_line = kwargs.pop("kws_line", kwargs)
-            ax = sns.lineplot(ax=ax, data=data, x=x, y=y, hue=hue, **kws_line)
+            ax = sns.lineplot(ax=ax, data=data, x=x, y=y, **kws_line)
 
         figsets(**kws_figsets)
         print(k, " ⤵ ")

py2ls/update2usage.py

@@ -0,0 +1,126 @@
+from .ips import *
+from .netfinder import fetch, get_soup
+
+
+def update_pd_usages(
+    url="https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.to_clipboard.html",
+    dir_save=None,
+):
+    # extract each usage from its url
+    def get_usage(url):
+        # extract each usage from its url
+        sp = get_soup(url, driver="se")
+        return fetch(sp, where="dt")[0]
+
+    if dir_save is None:
+        if "mac" in get_os():
+            dir_save = "/Users/macjianfeng/Dropbox/github/python/py2ls/py2ls/data/"
+        else:
+            dir_save = "Z:\\Jianfeng\\temp\\"
+    sp = get_soup(url, driver="se")
+    links_all = fetch(sp, where="a", get="href", class_="reference internal")
+    filtered_links = unique(
+        [i for i in links_all if any([i.startswith(cond) for cond in ["pandas"]])]
+    )
+    links = [
+        "https://pandas.pydata.org/docs/reference/api/" + i for i in filtered_links
+    ]
+
+    usages = [get_usage(i) for i in links]
+    dict_usage = {}
+    for usage in usages:
+        if usage.startswith("DataFrame"):
+            usage = usage.replace("DataFrame", "df")
+        if usage.startswith("pandas"):
+            usage = usage.replace("pandas", "pd")
+        if usage.endswith("[source]#"):
+            usage = usage.replace("[source]#", "")
+        if usage.endswith("#"):
+            usage = usage.replace("#", "")
+        str2rm = ["class", "property"]
+        for str2rm_ in str2rm:
+            if usage.startswith(str2rm_):
+                usage = usage.replace(str2rm, "")
+        funcname = ssplit(usage, by="(")[0]
+        dict_usage.update({funcname: usage})
+    # save to local
+    dir_save += "/" if not dir_save.endswith("/") else ""
+    fsave(
+        dir_save + "usages_pd.json",
+        dict_usage,
+    )
+
+
+def update_sns_usages(
+    url="https://seaborn.pydata.org/generated/seaborn.swarmplot.html",
+    dir_save=None,
+):
+    """
+    Fetches usage examples of various Seaborn plotting functions from the Seaborn documentation website.
+    It filters the relevant plot-related links, extracts usage examples, and saves them in a JSON file.
+
+    Parameters:
+    - url (str): URL of the Seaborn page to start extracting plot usages (default is swarmplot page).
+    - dir_save (str): Directory where the JSON file containing usages will be saved (default is a local path).
+
+    Saves:
+    - A JSON file named 'usages_sns.json' containing plotting function names and their usage descriptions.
+
+    Returns:
+    - None
+    """
+
+    # extract each usage from its url
+    def get_usage(url):
+        sp = get_soup(url, driver="se")
+        # preview(sp)
+        return fetch(sp, where="dt")[0]
+
+    if dir_save is None:
+        if "mac" in get_os():
+            dir_save = "/Users/macjianfeng/Dropbox/github/python/py2ls/py2ls/data/"
+        else:
+            dir_save = "Z:\\Jianfeng\\temp\\"
+    sp = get_soup(url, driver="se")
+    links_all = fetch(sp, where="a", get="href", class_="reference internal")
+    filtered_links = unique(
+        [
+            i
+            for i in links_all
+            if not any(
+                [
+                    i.startswith(cond)
+                    for cond in [
+                        "seaborn.JointGrid",
+                        "seaborn.PairGrid",
+                        "seaborn.objects",
+                    ]
+                ]
+                + ["plot" not in i]
+            )
+        ]
+    )
+    links = ["https://seaborn.pydata.org/generated/" + i for i in filtered_links]
+
+    usages = [get_usage(i) for i in links]
+    dict_usage = {}
+    for usage in usages:
+        dict_usage.update(
+            {ssplit(usage, by="(")[0].replace("seaborn.", ""): usage[:-1]}
+        )
+    # save to local
+    dir_save += "/" if not dir_save.endswith("/") else ""
+    fsave(
+        dir_save + "usages_sns.json",
+        dict_usage,
+    )
+
+
+def main():
+    # update pandas usage to local
+    update_pd_usages()
+    # update_sns_usages()
+
+
+if __name__ == "__main__":
+    main()

{py2ls-0.2.2.dist-info → py2ls-0.2.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: py2ls
-Version: 0.2.2
+Version: 0.2.3
 Summary: py(thon)2(too)ls
 Author: Jianfeng
 Author-email: Jianfeng.Liu0413@gmail.com

{py2ls-0.2.2.dist-info → py2ls-0.2.3.dist-info}/RECORD

@@ -1,4 +1,4 @@
-py2ls/.DS_Store,sha256=BloZZz2vlFVfF-I3X7ZsqXusvqOawJMx7erKcnIP-b0,6148
+py2ls/.DS_Store,sha256=N6pp6R6M5ZPDw6IdIAnsHaAAOu8hWJASHMjjjKMNmOc,6148
 py2ls/.git/COMMIT_EDITMSG,sha256=AdtqRHle5Ej2EBNPJY79v-SB454v5UK4wuPCPFELiFQ,11
 py2ls/.git/FETCH_HEAD,sha256=VM-2Jiw6iPaGu0ftg9xwq76OyNPWV0iT1nL0VWiL1zI,100
 py2ls/.git/HEAD,sha256=KNJb-Cr0wOK3L1CVmyvrhZ4-YLljCl6MYD2tTdsrboA,21
@@ -203,21 +203,23 @@ py2ls/data/styles/style6.json,sha256=tu-MYOT9x5Rorc-2IK6sy-J-frmz0RNdm65XAsDQKX4
 py2ls/data/styles/style7.json,sha256=StdUFwIVrS7T_6CDrADHMorzc0WZFWBM7IyYdO1TPHg,4447
 py2ls/data/styles/style8.json,sha256=8XUgkZtew8ebvjbAHlDHCSWUqNra3ktDvMCO4vNh-CM,4456
 py2ls/data/styles/style9.json,sha256=PLxvntbH_kfzZlnCTtCEAUVBGi5m6Lngb9C01rArQog,4769
+py2ls/data/usages_pd.json,sha256=XvFAwxKn6yYZztxmAhcqQ-kuYm6xBnLRx5aOLfvp3BQ,11060
 py2ls/data/usages_sns.json,sha256=Vu2kGIIMxxWxJ1kW0Ov7mq47DQwZa_-gwsXiW72A2ag,7788
 py2ls/db2ls.py,sha256=MMfFX47aIPIyu7fU9aPvX9lbPRPYOpJ_VXwlnWk-8qo,13615
 py2ls/doc.py,sha256=xN3g1OWfoaGUhikbJ0NqbN5eKy1VZVvWwRlhHMgyVEc,4243
 py2ls/export_requirements.py,sha256=x2WgUF0jYKz9GfA1MVKN-MdsM-oQ8yUeC6Ua8oCymio,2325
 py2ls/freqanalysis.py,sha256=F4218VSPbgL5tnngh6xNCYuNnfR-F_QjECUUxrPYZss,32594
 py2ls/ich2ls.py,sha256=3E9R8oVpyYZXH5PiIQgT3CN5NxLe4Dwtm2LwaeacE6I,21381
-py2ls/ips.py,sha256=HzdfzVViyIkgarkU7WWTtgXO3zS_ZwwDISGaKJUQ49E,193975
+py2ls/ips.py,sha256=uEpvsKo_E9eX49Icd60g-fQBDzmpGW65hJM9_mr6wuM,195254
 py2ls/netfinder.py,sha256=vgOOMhzwbjRuLWMAPyf_kh3HoOhsJ9dlA-tCkMf7kNU,55371
 py2ls/ocr.py,sha256=5lhUbJufIKRSOL6wAWVLEo8TqMYSjoI_Q-IO-_4u3DE,31419
-py2ls/plot.py,sha256=N6Rap4kX5xhae__WQG_YkBU8uSOH94IAxmoxZm2Wo9Q,129280
+py2ls/plot.py,sha256=ynL5fz2jf1pD09FWkAayQOT3c4Jj64sjFHrkgCqdgAs,127193
 py2ls/setuptools-70.1.0-py3-none-any.whl,sha256=2bi3cUVal8ip86s0SOvgspteEF8SKLukECi-EWmFomc,882588
 py2ls/sleep_events_detectors.py,sha256=bQA3HJqv5qnYKJJEIhCyhlDtkXQfIzqksnD0YRXso68,52145
 py2ls/stats.py,sha256=DMoJd8Z5YV9T1wB-4P52F5K5scfVK55DT8UP4Twcebo,38627
 py2ls/translator.py,sha256=zBeq4pYZeroqw3DT-5g7uHfVqKd-EQptT6LJ-Adi8JY,34244
+py2ls/update2usage.py,sha256=9uLoipgM0k-xUy56XOa6v-sOim3mE5srdNiPzn03ALY,3964
 py2ls/wb_detector.py,sha256=7y6TmBUj9exCZeIgBAJ_9hwuhkDh1x_-yg4dvNY1_GQ,6284
-py2ls-0.2.2.dist-info/METADATA,sha256=IWoyyv2E8mcEblmBAyXYkVvrPncuRqSV1Ys-CpENv6Y,20036
-py2ls-0.2.2.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
-py2ls-0.2.2.dist-info/RECORD,,
+py2ls-0.2.3.dist-info/METADATA,sha256=QvoGrLUwlS0T7VI09f-OJ8tU1Z3VGCl0bJWbP73RCCg,20036
+py2ls-0.2.3.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
+py2ls-0.2.3.dist-info/RECORD,,