diff --git a/LICENSE.txt b/LICENSE.txt index e8616ff3e..7c661a9d0 100644 --- a/LICENSE.txt +++ b/LICENSE.txt @@ -186,7 +186,7 @@ same "printed page" as the copyright notice for easier identification within third-party archives. - Copyright [2018] Microfocus + Copyright [2018-2025] Open Text Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. diff --git a/README.md b/README.md index 2730c9b00..eeb5c2146 100755 --- a/README.md +++ b/README.md @@ -243,7 +243,7 @@ selected_titanic.groupby(columns=["pclass"], expr=["AVG(AVG)"]) ### Charts -Verticapy comes integrated with three popular plotting libraries: matplotlib, highcharts, and plotly. +VerticaPy comes integrated with three popular plotting libraries: matplotlib, highcharts, and plotly. A gallery of VerticaPy-generated charts is available at:
@@ -367,7 +367,7 @@ set_option("sql_on", True) ```sql   SELECT -    /*+LABEL('vDataframe._aggregate_matrix')*/ CORR_MATRIX("pclass", "survived", "age", "sibsp", "parch", "fare", "body") OVER ()   +    /*+LABEL('vDataFrame._aggregate_matrix')*/ CORR_MATRIX("pclass", "survived", "age", "sibsp", "parch", "fare", "body") OVER ()     FROM (   SELECT diff --git a/docs/source/contribution_guidelines_code_auto_doc.rst b/docs/source/contribution_guidelines_code_auto_doc.rst index 7ce2f30a6..a08071a1d 100644 --- a/docs/source/contribution_guidelines_code_auto_doc.rst +++ b/docs/source/contribution_guidelines_code_auto_doc.rst @@ -73,7 +73,7 @@ Install the requirements by:  -Install Verticapy from the setup file using below in the VerticaPy directory +Install VerticaPy from the setup file using below in the VerticaPy directory .. code-block:: diff --git a/docs/source/index.rst b/docs/source/index.rst index cf5bd048f..cf196d3f4 100644 --- a/docs/source/index.rst +++ b/docs/source/index.rst @@ -43,7 +43,7 @@ Vertica database using the Python programming language. Vertica is a high-perfor :class-card: custom-card-2 :class-img-top: custom-class-img-top - Quick and easy guide to help you install Verticapy. + Quick and easy guide to help you install VerticaPy. +++ Install VerticaPy diff --git a/docs/source/pipeline.rst b/docs/source/pipeline.rst index b3944c812..36b8e3d11 100755 --- a/docs/source/pipeline.rst +++ b/docs/source/pipeline.rst @@ -16,7 +16,7 @@ To begin, you must: * Have access to a machine that has Vertica installed * Install Python on your machine -* Install Verticapy +* Install VerticaPy Create Your First YAML files ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -30,7 +30,7 @@ Create Your First YAML files - the files should have **.yaml** as the extension, - YAML does not allow the use of tabs while creating YAML files -The information in connection.yaml will be the same you use in Verticapy. +The information in connection.yaml will be the same you use in VerticaPy. .. code:: bash diff --git a/docs/source/user_guide_full_stack_dblink_integration.rst b/docs/source/user_guide_full_stack_dblink_integration.rst index 6186b9d7b..776679b4b 100644 --- a/docs/source/user_guide_full_stack_dblink_integration.rst +++ b/docs/source/user_guide_full_stack_dblink_integration.rst @@ -189,7 +189,7 @@ Let's try an example with the :py:func:`~verticapy.vDataFrame.describe` function -- Computing the descriptive statistics of all numerical columns using SUMMARIZE_NUMCOL SELECT - /*+LABEL('vDataframe.describe')*/ SUMMARIZE_NUMCOL("LATITUDE", "LONGITUDE") OVER () + /*+LABEL('vDataFrame.describe')*/ SUMMARIZE_NUMCOL("LATITUDE", "LONGITUDE") OVER () FROM ( SELECT "IATA_CODE", @@ -676,7 +676,7 @@ We can now perform the same query involving the three tables: Conclusion ----------- -With the combination of Verticapy and ``DBLINK``, we can now work with multiple datasets stored in different databases. We can work simultaneously with external tables, Vertica tables, and Pandas DataFrame in a **single query**! There is no need to materialize the table before use because it's all taken care of in the background. +With the combination of VerticaPy and ``DBLINK``, we can now work with multiple datasets stored in different databases. We can work simultaneously with external tables, Vertica tables, and Pandas DataFrame in a **single query**! There is no need to materialize the table before use because it's all taken care of in the background. The cherry on the cake is the ease-of-use that is enabled by VerticaPy and its Python-like syntax. diff --git a/docs/source/user_guide_introduction_vdf.rst b/docs/source/user_guide_introduction_vdf.rst index 6b9230017..f9364b766 100644 --- a/docs/source/user_guide_introduction_vdf.rst +++ b/docs/source/user_guide_introduction_vdf.rst @@ -237,7 +237,7 @@ We can also view the vDataFrame's backend SQL code generation by setting the ``s -- Computing the different aggregations SELECT - /*+LABEL('vDataframe.aggregate')*/ + /*+LABEL('vDataFrame.aggregate')*/ APPROXIMATE_COUNT_DISTINCT("cnt") FROM ( SELECT @@ -268,7 +268,7 @@ We can also view the vDataFrame's backend SQL code generation by setting the ``s -- Computing the descriptive statistics of all numerical columns using SUMMARIZE_NUMCOL SELECT - /*+LABEL('vDataframe.describe')*/ + /*+LABEL('vDataFrame.describe')*/ SUMMARIZE_NUMCOL("cnt") OVER () FROM ( SELECT diff --git a/examples/learn/titanic/titanic.ipynb b/examples/learn/titanic/titanic.ipynb index 7a870456e..1cb7b89b9 100644 --- a/examples/learn/titanic/titanic.ipynb +++ b/examples/learn/titanic/titanic.ipynb @@ -3177,7 +3177,7 @@ { "data": { "text/html": [ - "   SELECT
    /*+LABEL('vDataframe.aggregate')*/ 2.28444084278768,
    0.364667747163695,
    AVG(\"sex\"),
    AVG(\"age\"),
    0.504051863857374,
    0.378444084278768,
    AVG(\"fare\"),
    0.355753646677472,
    AVG(\"family_size\")  
  FROM
(
  SELECT
    \"pclass\",
    \"survived\",
    \"name\",
    \"sex\",
    COALESCE(\"age\", AVG(\"age\") OVER (PARTITION BY \"pclass\", \"sex\")) AS \"age\",
    \"sibsp\",
    \"parch\",
    \"fare\",
    \"boat\",
    \"family_size\"  
  FROM
(
  SELECT
    \"pclass\",
    \"survived\",
    REGEXP_SUBSTR(\"name\", ' ([A-Za-z]+)\\.') AS \"name\",
    DECODE(\"sex\", 'female', 0, 'male', 1, 2) AS \"sex\",
    \"age\",
    \"sibsp\",
    \"parch\",
    (CASE WHEN \"fare\" < -176.6204982585513 THEN -176.6204982585513 WHEN \"fare\" > 244.5480856064831 THEN 244.5480856064831 ELSE \"fare\" END) AS \"fare\",
    DECODE(\"boat\", NULL, 0, 1) AS \"boat\",
    ((\"parch\") + (\"sibsp\")) + (1) AS \"family_size\"  
  FROM
(  
  SELECT
    \"pclass\",
    \"survived\",
    \"name\",
    \"sex\",
    \"age\",
    \"sibsp\",
    \"parch\",
    \"fare\",
    \"boat\"  
  FROM
\"public\".\"titanic\")  
VERTICAPY_SUBTABLE)  
VERTICAPY_SUBTABLE)  
VERTICAPY_SUBTABLE  
  LIMIT 1" + "   SELECT
    /*+LABEL('vDataFrame.aggregate')*/ 2.28444084278768,
    0.364667747163695,
    AVG(\"sex\"),
    AVG(\"age\"),
    0.504051863857374,
    0.378444084278768,
    AVG(\"fare\"),
    0.355753646677472,
    AVG(\"family_size\")  
  FROM
(
  SELECT
    \"pclass\",
    \"survived\",
    \"name\",
    \"sex\",
    COALESCE(\"age\", AVG(\"age\") OVER (PARTITION BY \"pclass\", \"sex\")) AS \"age\",
    \"sibsp\",
    \"parch\",
    \"fare\",
    \"boat\",
    \"family_size\"  
  FROM
(
  SELECT
    \"pclass\",
    \"survived\",
    REGEXP_SUBSTR(\"name\", ' ([A-Za-z]+)\\.') AS \"name\",
    DECODE(\"sex\", 'female', 0, 'male', 1, 2) AS \"sex\",
    \"age\",
    \"sibsp\",
    \"parch\",
    (CASE WHEN \"fare\" < -176.6204982585513 THEN -176.6204982585513 WHEN \"fare\" > 244.5480856064831 THEN 244.5480856064831 ELSE \"fare\" END) AS \"fare\",
    DECODE(\"boat\", NULL, 0, 1) AS \"boat\",
    ((\"parch\") + (\"sibsp\")) + (1) AS \"family_size\"  
  FROM
(  
  SELECT
    \"pclass\",
    \"survived\",
    \"name\",
    \"sex\",
    \"age\",
    \"sibsp\",
    \"parch\",
    \"fare\",
    \"boat\"  
  FROM
\"public\".\"titanic\")  
VERTICAPY_SUBTABLE)  
VERTICAPY_SUBTABLE)  
VERTICAPY_SUBTABLE  
  LIMIT 1" ], "text/plain": [ "" @@ -3258,7 +3258,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "Let's move on to modeling our data. Save the vDataframe to your Vertica database." + "Let's move on to modeling our data. Save the vDataFrame to your Vertica database." ] }, { diff --git a/verticapy/_config/config.py b/verticapy/_config/config.py index f62ec1b9a..6401c474b 100755 --- a/verticapy/_config/config.py +++ b/verticapy/_config/config.py @@ -602,7 +602,7 @@ def set_option(key: str, value: Any = None) -> None: **Computing the different aggregations**. - SELECT /*+LABEL('vDataframe.aggregate')*/ MAX("age") FROM "public"."titanic" LIMIT 1 + SELECT /*+LABEL('vDataFrame.aggregate')*/ MAX("age") FROM "public"."titanic" LIMIT 1 **Execution**: 0.072s diff --git a/verticapy/core/vdataframe/_aggregate.py b/verticapy/core/vdataframe/_aggregate.py index 48494e9a0..a05c51d16 100755 --- a/verticapy/core/vdataframe/_aggregate.py +++ b/verticapy/core/vdataframe/_aggregate.py @@ -592,7 +592,7 @@ def aggregate( res = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.aggregate')*/ + /*+LABEL('vDataFrame.aggregate')*/ {", ".join([str(item) for sublist in agg for item in sublist])}""", print_time_sql=False, method="fetchrow", @@ -601,7 +601,7 @@ def aggregate( res = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.aggregate')*/ + /*+LABEL('vDataFrame.aggregate')*/ {", ".join([str(item) for sublist in agg for item in sublist])} FROM {self} LIMIT 1""", @@ -642,7 +642,7 @@ def aggregate( query = f""" WITH vdf_table AS (SELECT - /*+LABEL('vDataframe.aggregate')*/ * + /*+LABEL('vDataFrame.aggregate')*/ * FROM {self}) {query}""" if nb_precomputed == len(func) * len(columns): result = _executeSQL(query, print_time_sql=False, method="fetchall") @@ -674,7 +674,7 @@ def aggregate( _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.aggregate')*/ + /*+LABEL('vDataFrame.aggregate')*/ {columns_str} FROM {self}""", title=( @@ -702,7 +702,7 @@ def aggregate( result = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.aggregate')*/ + /*+LABEL('vDataFrame.aggregate')*/ {agg_fun} FROM {self}""", title=( @@ -1043,7 +1043,7 @@ def describe( query_result = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.describe')*/ + /*+LABEL('vDataFrame.describe')*/ SUMMARIZE_NUMCOL({cols_to_compute_str}) OVER () FROM {self}""", title=( @@ -3418,7 +3418,7 @@ def duplicated( total = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.duplicated')*/ COUNT(*) + /*+LABEL('vDataFrame.duplicated')*/ COUNT(*) FROM {main_table}""", title="Computing the number of duplicates.", method="fetchfirstelem", @@ -3440,7 +3440,7 @@ def duplicated( result.count = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.duplicated')*/ COUNT(*) + /*+LABEL('vDataFrame.duplicated')*/ COUNT(*) FROM (SELECT {columns}, diff --git a/verticapy/core/vdataframe/_corr.py b/verticapy/core/vdataframe/_corr.py index 71d7368be..27f0b54e6 100755 --- a/verticapy/core/vdataframe/_corr.py +++ b/verticapy/core/vdataframe/_corr.py @@ -107,7 +107,7 @@ def _aggregate_matrix( """ query = f""" SELECT - /*+LABEL('vDataframe._aggregate_matrix')*/ + /*+LABEL('vDataFrame._aggregate_matrix')*/ CORR({columns[0]}{cast_0}, {columns[1]}{cast_1}) FROM {table}""" title = ( @@ -147,7 +147,7 @@ def _aggregate_matrix( return np.nan query = f""" SELECT - /*+LABEL('vDataframe._aggregate_matrix')*/ + /*+LABEL('vDataFrame._aggregate_matrix')*/ (AVG(DECODE({column_b}{cast_b}, 1, {column_n}{cast_n}, NULL)) - AVG(DECODE({column_b}{cast_b}, 0, @@ -168,7 +168,7 @@ def _aggregate_matrix( return 1 n, k, r = _executeSQL( query=f""" - SELECT /*+LABEL('vDataframe._aggregate_matrix')*/ + SELECT /*+LABEL('vDataFrame._aggregate_matrix')*/ COUNT(*) AS n, COUNT(DISTINCT {columns[0]}) AS k, COUNT(DISTINCT {columns[1]}) AS r @@ -257,7 +257,7 @@ def _aggregate_matrix( n_0 = f"{n_} * ({n_} - 1)/2" tau_b = f"({n_c} - {n_d}) / sqrt(({n_0} - {n_1}) * ({n_0} - {n_2}))" query = f""" - SELECT /*+LABEL('vDataframe._aggregate_matrix')*/ + SELECT /*+LABEL('vDataFrame._aggregate_matrix')*/ {tau_b} FROM (SELECT @@ -272,7 +272,7 @@ def _aggregate_matrix( title = f"Computing the kendall correlation between {columns[0]} and {columns[1]}." elif method == "cov": query = f""" - SELECT /*+LABEL('vDataframe._aggregate_matrix')*/ + SELECT /*+LABEL('vDataFrame._aggregate_matrix')*/ COVAR_POP({columns[0]}{cast_0}, {columns[1]}{cast_1}) FROM {self}""" title = ( @@ -328,7 +328,7 @@ def _aggregate_matrix( ) table = f"(SELECT {columns_str} FROM {self}) spearman_table" result = _executeSQL( - query=f"""SELECT /*+LABEL('vDataframe._aggregate_matrix')*/ + query=f"""SELECT /*+LABEL('vDataFrame._aggregate_matrix')*/ CORR_MATRIX({', '.join(columns)}) OVER () FROM {table}""", @@ -441,7 +441,7 @@ def _aggregate_matrix( result = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe._aggregate_matrix')*/ + /*+LABEL('vDataFrame._aggregate_matrix')*/ {', '.join(all_list)}""", print_time_sql=False, method="fetchrow", @@ -450,7 +450,7 @@ def _aggregate_matrix( result = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe._aggregate_matrix')*/ + /*+LABEL('vDataFrame._aggregate_matrix')*/ {', '.join(all_list)} FROM {table}""", title=title, @@ -657,7 +657,7 @@ def _aggregate_vector( result = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe._aggregate_vector')*/ + /*+LABEL('vDataFrame._aggregate_vector')*/ {', '.join(all_list)}""", method="fetchrow", print_time_sql=False, @@ -666,7 +666,7 @@ def _aggregate_vector( result = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe._aggregate_vector')*/ + /*+LABEL('vDataFrame._aggregate_vector')*/ {', '.join(all_list)} FROM {table} LIMIT 1""", @@ -1028,7 +1028,7 @@ def corr_pvalue( val = self.corr(columns=[column1, column2], method=method) sql = f""" SELECT - /*+LABEL('vDataframe.corr_pvalue')*/ COUNT(*) + /*+LABEL('vDataFrame.corr_pvalue')*/ COUNT(*) FROM {self} WHERE {column1} IS NOT NULL AND {column2} IS NOT NULL;""" n = _executeSQL( @@ -1076,7 +1076,7 @@ def corr_pvalue( nc, nd = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.corr_pvalue')*/ + /*+LABEL('vDataFrame.corr_pvalue')*/ {n_c}::float, {n_d}::float FROM {table};""", @@ -1092,7 +1092,7 @@ def corr_pvalue( vt, v1_0, v2_0 = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.corr_pvalue')*/ + /*+LABEL('vDataFrame.corr_pvalue')*/ SUM(ni * (ni - 1) * (2 * ni + 5)), SUM(ni * (ni - 1)), SUM(ni * (ni - 1) * (ni - 2)) @@ -1110,7 +1110,7 @@ def corr_pvalue( vu, v1_1, v2_1 = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.corr_pvalue')*/ + /*+LABEL('vDataFrame.corr_pvalue')*/ SUM(ni * (ni - 1) * (2 * ni + 5)), SUM(ni * (ni - 1)), SUM(ni * (ni - 1) * (ni - 2)) @@ -1132,7 +1132,7 @@ def corr_pvalue( if kendall_type == "c": k, r = _executeSQL( query=f""" - SELECT /*+LABEL('vDataframe.corr_pvalue')*/ + SELECT /*+LABEL('vDataFrame.corr_pvalue')*/ APPROXIMATE_COUNT_DISTINCT({column1}) AS k, APPROXIMATE_COUNT_DISTINCT({column2}) AS r FROM {self} @@ -1149,7 +1149,7 @@ def corr_pvalue( elif method == "cramer": k, r = _executeSQL( query=f""" - SELECT /*+LABEL('vDataframe.corr_pvalue')*/ + SELECT /*+LABEL('vDataFrame.corr_pvalue')*/ COUNT(DISTINCT {column1}) AS k, COUNT(DISTINCT {column2}) AS r FROM {self} @@ -1541,7 +1541,7 @@ def regr( result = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.regr')*/ + /*+LABEL('vDataFrame.regr')*/ {", ".join(all_list)}""", print_time_sql=False, method="fetchrow", @@ -1550,7 +1550,7 @@ def regr( result = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.regr')*/ + /*+LABEL('vDataFrame.regr')*/ {", ".join(all_list)} FROM {self}""", title=f"Computing the {method.upper()} Matrix.", @@ -1569,7 +1569,7 @@ def regr( _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.regr')*/ + /*+LABEL('vDataFrame.regr')*/ {method.upper()}({columns[i]}{cast_i}, {columns[j]}{cast_j}) FROM {self}""", @@ -2050,7 +2050,7 @@ def pacf( drop(tmp_view_name, method="view") query = f""" CREATE VIEW {tmp_view_name} - AS SELECT /*+LABEL('vDataframe.pacf')*/ * FROM {relation}""" + AS SELECT /*+LABEL('vDataFrame.pacf')*/ * FROM {relation}""" _executeSQL(query, print_time_sql=False) vdf = create_new_vdf(tmp_view_name) model = vml.LinearRegression(solver="newton") diff --git a/verticapy/core/vdataframe/_encoding.py b/verticapy/core/vdataframe/_encoding.py index 70f9ee734..d586a17c5 100755 --- a/verticapy/core/vdataframe/_encoding.py +++ b/verticapy/core/vdataframe/_encoding.py @@ -268,7 +268,7 @@ def one_hot_encode( .. raw:: html :file: SPHINX_DIRECTORY/figures/core_vDataFrame_encoding_ohe1.html - Let's apply encoding on all the vcolumns of the datasets + Let's apply encoding on all the vDataColumns of the datasets .. code-block:: python @@ -285,7 +285,7 @@ def one_hot_encode( .. raw:: html :file: SPHINX_DIRECTORY/figures/core_vDataFrame_encoding_ohe2.html - Let's apply encoding on two specific vcolumns viz. "pclass" and "embarked" + Let's apply encoding on two specific vDataColumns viz. "pclass" and "embarked" .. code-block:: python @@ -444,7 +444,7 @@ def cut( data = vpd.load_titanic() - Let's look at "age" vcolumn + Let's look at "age" vDataColumn .. code-block:: python @@ -714,7 +714,7 @@ def decode(self, *args) -> "vDataFrame": data = vpd.load_titanic() - Let's encode "sex" vcolumn and represent "female" category as 1 and + Let's encode "sex" vDataColumn and represent "female" category as 1 and "male" category as 0. .. code-block:: python @@ -861,7 +861,7 @@ def discretize( data = vpd.load_titanic() - Let's look at "age" vcolumn + Let's look at "age" vDataColumn .. code-block:: python @@ -1292,7 +1292,7 @@ def one_hot_encode( .. raw:: html :file: SPHINX_DIRECTORY/figures/core_vDataFrame_encoding_ohe1.html - Let's apply encoding on "embarked" vcolumn. + Let's apply encoding on "embarked" vDataColumn. .. code-block:: python @@ -1465,7 +1465,7 @@ def label_encode(self) -> "vDataFrame": data = vpd.load_titanic() - Let's encode "embarked" vcolumn + Let's encode "embarked" vDataColumn .. code-block:: python @@ -1602,7 +1602,7 @@ def mean_encode(self, response: str) -> "vDataFrame": :file: SPHINX_DIRECTORY/figures/core_vDataFrame_encoding_mean_encode1.html Let's apply mean encoding which will replace each category of - "embarked" vcolumn by the average of the response + "embarked" vDataColumn by the average of the response .. code-block:: python diff --git a/verticapy/core/vdataframe/_filter.py b/verticapy/core/vdataframe/_filter.py index 39826d074..c29613a56 100755 --- a/verticapy/core/vdataframe/_filter.py +++ b/verticapy/core/vdataframe/_filter.py @@ -1168,7 +1168,7 @@ def filter( new_count = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.filter')*/ + /*+LABEL('vDataFrame.filter')*/ COUNT(*) FROM {self}""", title="Computing the new number of elements.", @@ -1319,7 +1319,7 @@ def first(self, ts: str, offset: str) -> "vDataFrame": first_date = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.first')*/ + /*+LABEL('vDataFrame.first')*/ (MIN({ts}) + '{offset}'::interval)::varchar FROM {self}""", title="Getting the vDataFrame first values.", @@ -1561,7 +1561,7 @@ def last(self, ts: str, offset: str) -> "vDataFrame": last_date = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.last')*/ + /*+LABEL('vDataFrame.last')*/ (MAX({ts}) - '{offset}'::interval)::varchar FROM {self}""", title="Getting the vDataFrame last values.", diff --git a/verticapy/core/vdataframe/_io.py b/verticapy/core/vdataframe/_io.py index 43ffe2195..f9c1dcb62 100755 --- a/verticapy/core/vdataframe/_io.py +++ b/verticapy/core/vdataframe/_io.py @@ -221,7 +221,7 @@ def load(self, offset: int = -1) -> "vDataFrame": data.save() Let's perform some operations on the - ``vDataframe``. + ``vDataFrame``. .. code-block:: python @@ -351,7 +351,7 @@ def save(self) -> "vDataFrame": data.save() Let's perform some operations on the - ``vDataframe``. + ``vDataFrame``. .. code-block:: python @@ -638,7 +638,7 @@ def to_csv( result = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.to_csv')*/ + /*+LABEL('vDataFrame.to_csv')*/ {', '.join(columns)} FROM {self} {order_by} @@ -1005,7 +1005,7 @@ def to_db( {name}{commit} AS SELECT - /*+LABEL('vDataframe.to_db')*/ + /*+LABEL('vDataFrame.to_db')*/ {select}{nb_split} FROM {self} {db_filter} @@ -1160,7 +1160,7 @@ def to_geopandas(self, geometry: str) -> "GeoDataFrame": columns = ", ".join(columns + [f"ST_AsText({geometry}) AS {geometry}"]) query = f""" SELECT - /*+LABEL('vDataframe.to_geopandas')*/ {columns} + /*+LABEL('vDataFrame.to_geopandas')*/ {columns} FROM {self} {self._get_last_order_by()}""" data = _executeSQL( @@ -1373,7 +1373,7 @@ def to_json( result = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.to_json')*/ + /*+LABEL('vDataFrame.to_json')*/ {', '.join(transformations)} FROM {self} {order_by} @@ -1507,7 +1507,7 @@ def to_list(self) -> list: res = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.to_list')*/ * + /*+LABEL('vDataFrame.to_list')*/ * FROM {self} {self._get_last_order_by()}""", title="Getting the vDataFrame values.", @@ -1725,7 +1725,7 @@ def to_pandas(self) -> pd.DataFrame: data = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.to_pandas')*/ * + /*+LABEL('vDataFrame.to_pandas')*/ * FROM {self}{self._get_last_order_by()}""", title="Getting the vDataFrame values.", method="fetchall", @@ -1909,7 +1909,7 @@ def to_parquet( .. note:: - It will export vDataframe to parquet + It will export vDataFrame to parquet file at provided directory. .. seealso:: @@ -2029,7 +2029,7 @@ def to_pickle(self, name: str) -> "vDataFrame": data.to_pickle("vdf_data.p") - Let's unpickle the vDataframe from Python + Let's unpickle the vDataFrame from Python pickle file and view it. .. code-block:: python @@ -2200,7 +2200,7 @@ def to_shp( usecols = format_type(usecols, dtype=list) query = f""" SELECT - /*+LABEL('vDataframe.to_shp')*/ + /*+LABEL('vDataFrame.to_shp')*/ STV_SetExportShapefileDirectory( USING PARAMETERS path = '{path}');""" _executeSQL(query=query, title="Setting SHP Export directory.") @@ -2208,7 +2208,7 @@ def to_shp( columns = ", ".join(columns) query = f""" SELECT - /*+LABEL('vDataframe.to_shp')*/ + /*+LABEL('vDataFrame.to_shp')*/ STV_Export2Shapefile({columns} USING PARAMETERS shapefile = '{name}.shp', overwrite = {overwrite}, diff --git a/verticapy/core/vdataframe/_machine_learning.py b/verticapy/core/vdataframe/_machine_learning.py index 5ebf03fc1..6d8ac2bd0 100755 --- a/verticapy/core/vdataframe/_machine_learning.py +++ b/verticapy/core/vdataframe/_machine_learning.py @@ -524,7 +524,7 @@ def chaid( result = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.chaid')*/ + /*+LABEL('vDataFrame.chaid')*/ {split_predictor}, {response}, (cnt / SUM(cnt) @@ -1987,7 +1987,7 @@ def train_test_split( test_size: float = 0.33, order_by: Union[None, str, list, dict] = None, random_state: int = None, - ) -> tuple["vDataframe", "vDataFrame"]: + ) -> tuple["vDataFrame", "vDataFrame"]: """ Creates two vDataFrames (train/test), which can be used to evaluate a model. The intersection between the train @@ -2096,7 +2096,7 @@ def train_test_split( q = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.train_test_split')*/ + /*+LABEL('vDataFrame.train_test_split')*/ APPROXIMATE_PERCENTILE({random_func} USING PARAMETERS percentile = {test_size}) FROM {self}""", diff --git a/verticapy/core/vdataframe/_pivot.py b/verticapy/core/vdataframe/_pivot.py index 07d093d1f..c494e7f97 100755 --- a/verticapy/core/vdataframe/_pivot.py +++ b/verticapy/core/vdataframe/_pivot.py @@ -715,7 +715,7 @@ def explode_array( vdf = create_new_vdf( f""" SELECT - /*+LABEL('vDataframe.explode')*/ + /*+LABEL('vDataFrame.explode')*/ {index}, {column}, EXPLODE({column} diff --git a/verticapy/core/vdataframe/_read.py b/verticapy/core/vdataframe/_read.py index e849ec873..ea1723c2a 100755 --- a/verticapy/core/vdataframe/_read.py +++ b/verticapy/core/vdataframe/_read.py @@ -84,7 +84,7 @@ def __getitem__(self, index: Any) -> Any: index += self.shape()[0] return _executeSQL( query=f""" - SELECT /*+LABEL('vDataframe.__getitem__')*/ + SELECT /*+LABEL('vDataFrame.__getitem__')*/ {', '.join(columns)} FROM {self} {self._get_last_order_by()} @@ -579,7 +579,7 @@ def shape(self) -> tuple[int, int]: self._vars["count"] = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.shape')*/ COUNT(*) + /*+LABEL('vDataFrame.shape')*/ COUNT(*) FROM {self} LIMIT 1 """, title="Computing the total number of elements (COUNT(*))", diff --git a/verticapy/core/vdataframe/_sys.py b/verticapy/core/vdataframe/_sys.py index 79f61bc2c..2e48ea1e9 100755 --- a/verticapy/core/vdataframe/_sys.py +++ b/verticapy/core/vdataframe/_sys.py @@ -800,7 +800,7 @@ def explain(self, digraph: bool = False) -> str: query=f""" EXPLAIN SELECT - /*+LABEL('vDataframe.explain')*/ * + /*+LABEL('vDataFrame.explain')*/ * FROM {self}""", title="Explaining the Current Relation", method="fetchall", diff --git a/verticapy/core/vdataframe/_typing.py b/verticapy/core/vdataframe/_typing.py index 7829c67b4..33a8501b1 100755 --- a/verticapy/core/vdataframe/_typing.py +++ b/verticapy/core/vdataframe/_typing.py @@ -110,7 +110,7 @@ def astype(self, dtype: dict) -> "vDataFrame": data = vpd.load_titanic() - Let's check the data types of various vcolumns. + Let's check the data types of various vDataColumns. .. code-block:: python @@ -127,13 +127,13 @@ def astype(self, dtype: dict) -> "vDataFrame": .. raw:: html :file: SPHINX_DIRECTORY/figures/core_vDataFrame_typing_astype1.html - Let's change the data type of few vcolumns. + Let's change the data type of few vDataColumns. .. code-block:: python data.astype({"fare": "int", "cabin": "varchar(1)"}) - Let's check the data type of various vcolumns again. + Let's check the data type of various vDataColumns again. .. code-block:: python @@ -307,14 +307,14 @@ def catcol(self, max_cardinality: int = 12) -> list: data = vpd.load_titanic() - Let's check the categorical vcolumns considering maximum + Let's check the categorical vDataColumns considering maximum cardinality as 10. .. ipython:: python data.catcol(max_cardinality = 10) - Let's again check the categorical vcolumns considering + Let's again check the categorical vDataColumns considering maximum cardinality as 6. .. ipython:: python @@ -336,7 +336,7 @@ def catcol(self, max_cardinality: int = 12) -> list: is_cat = _executeSQL( query=f""" SELECT - /*+LABEL('vDataframe.catcol')*/ + /*+LABEL('vDataFrame.catcol')*/ (APPROXIMATE_COUNT_DISTINCT({column}) < {max_cardinality}) FROM {self}""", title="Looking at columns with low cardinality.", @@ -430,7 +430,7 @@ def datecol(self) -> list: data["dob"].astype("date") data["doj"].astype("date") - Let's retrieve the date type vcolumns in the dataset. + Let's retrieve the date type vDataColumns in the dataset. .. ipython:: python @@ -512,7 +512,7 @@ def dtypes(self) -> TableSample: data = vpd.load_titanic() - Let's check the data type of various vcolumns. + Let's check the data type of various vDataColumns. .. code-block:: python @@ -606,7 +606,7 @@ def numcol(self, exclude_columns: Optional[SQLColumns] = None) -> list: .. raw:: html :file: SPHINX_DIRECTORY/figures/core_vDataFrame_typing_numcol.html - Let's retrieve the numeric type vcolumns in the dataset. + Let's retrieve the numeric type vDataColumns in the dataset. .. ipython:: python @@ -701,7 +701,7 @@ def astype(self, dtype: Union[str, type]) -> "vDataFrame": data = vpd.load_titanic() - Let's check the data type of fare vcolumn. + Let's check the data type of fare vDataColumn. .. ipython:: python @@ -718,7 +718,7 @@ def astype(self, dtype: Union[str, type]) -> "vDataFrame": data["fare"].astype(int) - Let's check the data type of fare vcolumn again. + Let's check the data type of fare vDataColumn again. .. ipython:: python @@ -940,7 +940,7 @@ def category(self) -> str: data = vpd.load_titanic() - Let's check the category of "fare" and "name" vcolumns. + Let's check the category of "fare" and "name" vDataColumns. .. ipython:: python @@ -1014,7 +1014,7 @@ def ctype(self) -> str: data = vpd.load_titanic() - Let's check the DB type of "fare" and "name" vcolumns. + Let's check the DB type of "fare" and "name" vDataColumns. .. ipython:: python @@ -1083,7 +1083,7 @@ def isarray(self) -> bool: .. raw:: html :file: SPHINX_DIRECTORY/figures/core_vDataFrame_typing_isarray.html - Let's check if data type of "artists" vcolumn is array or not. + Let's check if data type of "artists" vDataColumn is array or not. .. ipython:: python @@ -1152,13 +1152,13 @@ def isbool(self) -> bool: .. raw:: html :file: SPHINX_DIRECTORY/figures/core_vDataFrame_typing_isbool.html - Let's check if data type of "is_temp" vcolumn is bool or not. + Let's check if data type of "is_temp" vDataColumn is bool or not. .. ipython:: python data["is_temp"].isbool() - Let's check if data type of "empid" vcolumn is bool or not. + Let's check if data type of "empid" vDataColumn is bool or not. .. ipython:: python @@ -1228,13 +1228,13 @@ def isdate(self) -> bool: import verticapy.datasets as vpd amazon = vpd.load_amazon() - Let's check if the category of "date" vcolumn is date or not. + Let's check if the category of "date" vDataColumn is date or not. .. ipython:: python amazon["date"].isdate() - Let's check if the category of "state" vcolumn is date or not + Let's check if the category of "state" vDataColumn is date or not .. ipython:: python @@ -1303,7 +1303,7 @@ def isnum(self) -> bool: .. raw:: html :file: SPHINX_DIRECTORY/figures/core_vDataFrame_typing_isbool.html - Let's check if data type of "empid" vcolumn is numerical or not. + Let's check if data type of "empid" vDataColumn is numerical or not. .. ipython:: python @@ -1374,13 +1374,13 @@ def isvmap(self) -> bool: .. raw:: html :file: SPHINX_DIRECTORY/figures/core_vDataFrame_typing_isvmap.html - Let's check if data type of "mgr" vcolumn is vmap or not. + Let's check if data type of "mgr" vDataColumn is vmap or not. .. ipython:: python data["mgr"].isvmap() - Let's check if data type of "empid" vcolumn is vmap or not. + Let's check if data type of "empid" vDataColumn is vmap or not. .. ipython:: python diff --git a/verticapy/plotting/_plotly/bar.py b/verticapy/plotting/_plotly/bar.py index aa6cc796a..7304c5e39 100755 --- a/verticapy/plotting/_plotly/bar.py +++ b/verticapy/plotting/_plotly/bar.py @@ -110,11 +110,15 @@ def draw( Draws a 2D BarChart using the Matplotlib API. """ fig_base = self._get_fig(fig) + ncolors = len(self.get_colors()) for i in range(len(self.layout["y_labels"])): fig = go.Bar( name=self.layout["y_labels"][i], x=self.layout["x_labels"], y=self.data["X"][:, i], + marker=dict( + color=self.get_colors()[i % ncolors], + ), ) fig_base.add_trace(fig) params = self._update_dict(self.init_layout_style, style_kwargs) diff --git a/verticapy/plotting/_plotly/barh.py b/verticapy/plotting/_plotly/barh.py index c1be527b4..2d0edd4ce 100644 --- a/verticapy/plotting/_plotly/barh.py +++ b/verticapy/plotting/_plotly/barh.py @@ -110,6 +110,7 @@ def draw( """ n, m = self.data["X"].shape fig_base = self._get_fig(fig) + ncolors = len(self.get_colors()) if self.layout["kind"] == "fully_stacked": self.data["X"] = self.data["X"] / np.sum( self.data["X"], axis=1, keepdims=True @@ -129,6 +130,9 @@ def draw( y=self.layout["x_labels"], x=self.data["X"][:, i], orientation="h", + marker=dict( + color=self.get_colors()[i % ncolors], + ), ) fig_base.add_trace(fig) params = self._update_dict(self.init_layout_style, style_kwargs) diff --git a/verticapy/plotting/_plotly/hist.py b/verticapy/plotting/_plotly/hist.py index 119b73024..5c6a40a34 100644 --- a/verticapy/plotting/_plotly/hist.py +++ b/verticapy/plotting/_plotly/hist.py @@ -55,6 +55,7 @@ def draw( """ fig = self._get_fig(fig) key = "categories" if self.layout["has_category"] else "columns" + ncolors = len(self.get_colors()) for i in range(len(self.layout[key])): fig.add_trace( go.Bar( @@ -64,6 +65,9 @@ def draw( width=self.data["width"], offset=0, opacity=0.8 if len(self.layout[key]) > 1 else 1, + marker=dict( + color=self.get_colors()[i % ncolors], + ), ) ) fig.update_layout(yaxis_title=self.layout["method_of"]) diff --git a/verticapy/plotting/_plotly/machine_learning/importance.py b/verticapy/plotting/_plotly/machine_learning/importance.py index 30c33a828..e8eb1f0bc 100644 --- a/verticapy/plotting/_plotly/machine_learning/importance.py +++ b/verticapy/plotting/_plotly/machine_learning/importance.py @@ -73,6 +73,9 @@ def draw( y=self.layout["columns"], orientation="h", name="Postive", + marker=dict( + color=self.get_colors()[0], + ), ) ) showlegend = False @@ -83,6 +86,9 @@ def draw( y=self.layout["columns"], orientation="h", name="Negative", + marker=dict( + color=self.get_colors()[1], + ), ) ) showlegend = True diff --git a/verticapy/tests_new/core/vdataframe/test_agg.py b/verticapy/tests_new/core/vdataframe/test_agg.py index 3515bf033..b979e96ce 100644 --- a/verticapy/tests_new/core/vdataframe/test_agg.py +++ b/verticapy/tests_new/core/vdataframe/test_agg.py @@ -179,8 +179,8 @@ def test_groupby( [ ("vDataFrame", []), ("vDataFrame_column", ["age"]), - ("vcolumn", ["age"]), - ("vcolumn", ["age", "fare", "pclass", "survived"]), + ("vDataColumn", ["age"]), + ("vDataColumn", ["age", "fare", "pclass", "survived"]), ], ) @pytest.mark.parametrize("agg_func_type", ["agg", "aggregate"]) @@ -327,7 +327,7 @@ def test_aggregate( [ ("vDataFrame", []), ("vDataFrame_columns", ["age"]), - ("vcolumn", ["age", "fare", "pclass", "survived"]), + ("vDataColumn", ["age", "fare", "pclass", "survived"]), ], ) def test_vdf_vcol( @@ -469,7 +469,7 @@ def test_vdf(self, titanic_vd, func_name, vpy_func, py_func): ["value_counts", "topk", "distinct"], ) @pytest.mark.parametrize("columns", ["pclass"]) - def test_vcolumn(self, titanic_vd, columns, func_name): + def test_vDataColumn(self, titanic_vd, columns, func_name): """ test function - Vcolumn groupby """ diff --git a/verticapy/tests_new/core/vdataframe/test_correlation.py b/verticapy/tests_new/core/vdataframe/test_correlation.py index 753557b1c..50078041f 100644 --- a/verticapy/tests_new/core/vdataframe/test_correlation.py +++ b/verticapy/tests_new/core/vdataframe/test_correlation.py @@ -400,7 +400,7 @@ def test_regr(self, titanic_vd, columns, method, expected): [ ("vDataFrame", []), ("vDataFrame_column", ["sex", "pclass"]), - ("vcolumn", ["sex"]), + ("vDataColumn", ["sex"]), ], ) def test_iv_woe(self, titanic_vd, input_type, columns): @@ -436,7 +436,7 @@ def test_iv_woe(self, titanic_vd, input_type, columns): _iv = np.sum((freq_data[1] - freq_data[0]) * _woe) py_res.append(_iv) - py_res = py_res[0] if input_type == "vcolumn" else py_res + py_res = py_res[0] if input_type == "vDataColumn" else py_res print(f"VerticaPy Result: {vpy_res} \nPython Result :{py_res}\n") assert vpy_res == pytest.approx(py_res, abs=1e-03, rel=1e-03) diff --git a/verticapy/tests_new/core/vdataframe/test_fill.py b/verticapy/tests_new/core/vdataframe/test_fill.py index 3aa3e4699..391b7cecb 100644 --- a/verticapy/tests_new/core/vdataframe/test_fill.py +++ b/verticapy/tests_new/core/vdataframe/test_fill.py @@ -61,7 +61,10 @@ class TestFill: ) @pytest.mark.parametrize( "function_type, numeric_only, expr, by, order_by", - [("vDataFrame", None, None, None, None), ("vcolumn", None, None, None, None)], + [ + ("vDataFrame", None, None, None, None), + ("vDataColumn", None, None, None, None), + ], ) def test_fillna( self, diff --git a/verticapy/tests_new/core/vdataframe/test_filter.py b/verticapy/tests_new/core/vdataframe/test_filter.py index 87f4c7052..67d7840fc 100644 --- a/verticapy/tests_new/core/vdataframe/test_filter.py +++ b/verticapy/tests_new/core/vdataframe/test_filter.py @@ -163,7 +163,7 @@ def test_between_time(self, smart_meters_vd, ts, start_time, end_time, inplace): "age", ], ) - @pytest.mark.parametrize("function_type", ["vDataFrame", "vcolumn"]) + @pytest.mark.parametrize("function_type", ["vDataFrame", "vDataColumn"]) def test_drop(self, titanic_vd_fun, function_type, columns): """ test function - drop @@ -208,7 +208,7 @@ def test_drop_duplicates(self, winequality_vpy_fun, columns): "ticket", ], ) - @pytest.mark.parametrize("function_type", ["vDataFrame", "vcolumn"]) + @pytest.mark.parametrize("function_type", ["vDataFrame", "vDataColumn"]) def test_dropna(self, titanic_vd_fun, function_type, columns): """ test function - dropna @@ -281,7 +281,7 @@ def test_first(self, smart_meters_vd): "function_type, column, conditions", [ ("vDataFrame", None, {"sex": ["female"], "survived": [1], "parch": [1]}), - ("vcolumn", "sex", ["female"]), + ("vDataColumn", "sex", ["female"]), ], ) def test_isin(self, titanic_vd_fun, function_type, column, conditions): diff --git a/verticapy/tests_new/core/vdataframe/test_math.py b/verticapy/tests_new/core/vdataframe/test_math.py index c55cb31a9..946207cc7 100644 --- a/verticapy/tests_new/core/vdataframe/test_math.py +++ b/verticapy/tests_new/core/vdataframe/test_math.py @@ -39,8 +39,8 @@ class TestMath: ("vDataFrame", "age"), ("vDataFrame_column", "age"), ("vDataFrame_column", ["age", "fare", "pclass", "survived"]), - ("vcolumn", "age"), - ("vcolumn", ["age", "fare", "pclass", "survived"]), + ("vDataColumn", "age"), + ("vDataColumn", ["age", "fare", "pclass", "survived"]), ], ) def test_abs(self, titanic_vd_fun, input_type, columns): @@ -126,8 +126,8 @@ def test_binary_operator(self, titanic_vd_fun, func, columns, scalar): }, None, ), - (["age"], "vcolumn", "POWER({}, 2)", None), - (["age"], "vcolumn", "POWER({}, 2)", "age_pow2"), + (["age"], "vDataColumn", "POWER({}, 2)", None), + (["age"], "vDataColumn", "POWER({}, 2)", "age_pow2"), ], ) def test_apply(self, titanic_vd_fun, columns, input_type, func, copy_name): diff --git a/verticapy/tests_new/core/vdataframe/test_miscellaneous.py b/verticapy/tests_new/core/vdataframe/test_miscellaneous.py index 0a4dbea1f..6fcbe8491 100644 --- a/verticapy/tests_new/core/vdataframe/test_miscellaneous.py +++ b/verticapy/tests_new/core/vdataframe/test_miscellaneous.py @@ -25,7 +25,7 @@ class TestMiscellaneousVDF: """ - test class to test Miscellaneous functions for vDataframe + test class to test Miscellaneous functions for vDataFrame """ def test_repr(self, titanic_vd_fun): @@ -138,7 +138,7 @@ def test_sql(self, titanic_vd_fun, schema_loader): class TestVDFCreate: """ - test class to test vDataframe create options + test class to test vDataFrame create options """ def test_using_input_relation(self, titanic_vd_fun, schema_loader): diff --git a/verticapy/tests_new/core/vdataframe/test_read.py b/verticapy/tests_new/core/vdataframe/test_read.py index 85c081e68..01cba71b2 100644 --- a/verticapy/tests_new/core/vdataframe/test_read.py +++ b/verticapy/tests_new/core/vdataframe/test_read.py @@ -47,8 +47,8 @@ def test_get_columns(self, titanic_vd, exclude_columns): [ ("vDataFrame", "age", None), ("vDataFrame", "age", 10), - ("vcolumn", "ticket", 2), - ("vcolumn", "ticket", None), + ("vDataColumn", "ticket", 2), + ("vDataColumn", "ticket", None), ], ) @pytest.mark.parametrize("func", ["head", "tail"]) @@ -94,10 +94,10 @@ def test_head_tail(self, titanic_vd, func, function_type, columns, limit): ("vDataFrame", 4, 20, ["ticket", "home.dest"], None), ("vDataFrame", 4, None, ["ticket", "home.dest"], None), ("vDataFrame", None, 7, ["ticket"], None), - ("vcolumn", 2, 5, "ticket", "name"), - ("vcolumn", 2, None, "ticket", "name"), - ("vcolumn", None, 5, "ticket", "name"), - ("vcolumn", None, None, "ticket", "name"), + ("vDataColumn", 2, 5, "ticket", "name"), + ("vDataColumn", 2, None, "ticket", "name"), + ("vDataColumn", None, 5, "ticket", "name"), + ("vDataColumn", None, None, "ticket", "name"), ], ) def test_iloc( diff --git a/verticapy/tests_new/core/vdataframe/test_scaler.py b/verticapy/tests_new/core/vdataframe/test_scaler.py index ce044f860..eafaf8a49 100644 --- a/verticapy/tests_new/core/vdataframe/test_scaler.py +++ b/verticapy/tests_new/core/vdataframe/test_scaler.py @@ -29,7 +29,7 @@ class TestScaler: ) def test_scale_vdf(self, titanic_vd, columns, method): """ - test function - scaling for vDataframe + test function - scaling for vDataFrame """ titanic_pdf = titanic_vd.to_pandas() titanic_pdf[columns] = titanic_pdf[columns].astype(float) @@ -61,7 +61,7 @@ def test_scale_vdf(self, titanic_vd, columns, method): [("age", "zscore"), ("age", "robust_zscore"), ("age", "minmax")], ) @pytest.mark.parametrize("partition_by", ["pclass", None]) - def test_scale_vcolumn(self, titanic_vd_fun, partition_by, columns, method): + def test_scale_vDataColumn(self, titanic_vd_fun, partition_by, columns, method): """ test function - scaling for vDataColumns """ diff --git a/verticapy/tests_new/core/vdataframe/test_sys.py b/verticapy/tests_new/core/vdataframe/test_sys.py index 7e2e60588..1192265e8 100644 --- a/verticapy/tests_new/core/vdataframe/test_sys.py +++ b/verticapy/tests_new/core/vdataframe/test_sys.py @@ -19,7 +19,7 @@ class TestVDFSys: """ - test class for sys functions test for vDataframe class + test class for sys functions test for vDataFrame class """ def test_current_relation(self, titanic_vd_fun): diff --git a/verticapy/tests_new/core/vdataframe/test_text.py b/verticapy/tests_new/core/vdataframe/test_text.py index 1b0747524..6f7f30fa8 100644 --- a/verticapy/tests_new/core/vdataframe/test_text.py +++ b/verticapy/tests_new/core/vdataframe/test_text.py @@ -49,7 +49,7 @@ def test_regexp( name, ): """ - test function - regexp for vDataframe + test function - regexp for vDataFrame """ titanic_pdf = titanic_vd_fun.to_pandas() diff --git a/verticapy/tests_new/core/vdataframe/test_typing.py b/verticapy/tests_new/core/vdataframe/test_typing.py index 27117821d..4db1d26e7 100644 --- a/verticapy/tests_new/core/vdataframe/test_typing.py +++ b/verticapy/tests_new/core/vdataframe/test_typing.py @@ -34,7 +34,7 @@ class TestVDFTyping: def test_astype(self, titanic_vd_fun): """ - test function - astype for vDataframe + test function - astype for vDataFrame """ # Testing vDataFrame.astype titanic_vd_fun.astype({"fare": "int", "cabin": "varchar(1)"}) diff --git a/verticapy/tests_new/performance/vertica/test_qprof.py b/verticapy/tests_new/performance/vertica/test_qprof.py index 61dd572e8..7a7f5d96c 100644 --- a/verticapy/tests_new/performance/vertica/test_qprof.py +++ b/verticapy/tests_new/performance/vertica/test_qprof.py @@ -1515,7 +1515,7 @@ def test_get_qexecution( followed by sorting based on key column(s). **Steps to get expected result** - - Step 5: Get query execution report (vDataframe) using ``get_qexecution_report`` method, and repeat step 4 + - Step 5: Get query execution report (vDataFrame) using ``get_qexecution_report`` method, and repeat step 4 **Steps to compare actual and expected results** - Step 6: compare actual and expected pandas dataframe using pandas compare function.