Skip to content

Checking Compatibility

src.dx.datatypes.compatibility.test_compatibility(value, as_dataframe=True)

Convenience function to test the compatibility of a given object with the different steps involved with the dx display modes. - pandas.io.json.build_table_schema (https://github.com/pandas-dev/pandas/blob/main/pandas/io/json/_table_schema.py) - jupyter_client.jsonutil.json_clean (https://github.com/jupyter/jupyter_client/blob/main/jupyter_client/jsonutil.py) - duckdb conn.register - final dx output type

Parameters:

Name Type Description Default
value Any

The value to test compatibility with.

 required
as_dataframe bool

Whether to return the results as a pandas DataFrame (if True), or as a dictionary (if False)

 True
Source code in src/dx/datatypes/compatibility.py 
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
def test_compatibility(value: Any, as_dataframe: bool = True) -> dict:
    """
    Convenience function to test the compatibility of a given object
    with the different steps involved with the dx display modes.
    - `pandas.io.json.build_table_schema` (https://github.com/pandas-dev/pandas/blob/main/pandas/io/json/_table_schema.py)
    - `jupyter_client.jsonutil.json_clean` (https://github.com/jupyter/jupyter_client/blob/main/jupyter_client/jsonutil.py)
    - `duckdb conn.register`
    - final dx output type

    Parameters
    ----------
    value: Any
        The value to test compatibility with.
    as_dataframe: bool
        Whether to return the results as a pandas DataFrame (if `True`),
        or as a dictionary (if `False`)
    """
    result = {}
    result.update(test_build_table_schema(value))
    result.update(test_json_clean(value))
    result.update(test_db_write(value))
    result.update(test_dx_handling(value))
    if as_dataframe:
        return pd.DataFrame(result).transpose()
    return result

src.dx.datatypes.compatibility.test_build_table_schema(value, as_dataframe=False)

Convenience function to test the compatibility of a given object with the pandas.io.json.build_table_schema function, which is called to set up the initial column schema during dx formatting.

Parameters:

Name Type Description Default
value Any

The value to test compatibility with.

 required
as_dataframe bool

Whether to return the results as a pandas DataFrame (if True), or as a dictionary (if False)

 False
Source code in src/dx/datatypes/compatibility.py 
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
def test_build_table_schema(value: Any, as_dataframe: bool = False) -> dict:
    """
    Convenience function to test the compatibility of a given object
    with the pandas.io.json.build_table_schema function, which
    is called to set up the initial column schema during dx formatting.

    Parameters
    ----------
    value: Any
        The value to test compatibility with.
    as_dataframe: bool
        Whether to return the results as a pandas DataFrame (if `True`),
        or as a dictionary (if `False`)
    """
    df = pd.DataFrame({"test": [value]})
    result = {}

    try:
        schema = build_table_schema(df, index=False)
        fields = schema["fields"]
        field_type = [
            field_schema["type"] for field_schema in fields if field_schema["name"] == "test"
        ][0]
        result["pandas.io.json.build_table_schema"] = {
            "success": True,
            "type": field_type,
        }
    except Exception as e:
        result["pandas.io.json.build_table_schema"] = {
            "error": str(e),
            "success": False,
            "traceback": traceback.format_exc(),
        }

    if as_dataframe:
        return pd.DataFrame(result).transpose()
    return result

src.dx.datatypes.compatibility.test_json_clean(value, as_dataframe=False)

Convenience function to test the compatibility of a given object with the jupyter_client.jsonutil.json_clean function, which is called during IPython.display after dx formatting.

Parameters:

Name Type Description Default
value Any

The value to test compatibility with.

 required
as_dataframe bool

Whether to return the results as a pandas DataFrame (if True), or as a dictionary (if False)

 False
Source code in src/dx/datatypes/compatibility.py 
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
def test_json_clean(value: Any, as_dataframe: bool = False) -> dict:
    """
    Convenience function to test the compatibility of a given object
    with the jupyter_client.jsonutil.json_clean function, which
    is called during IPython.display after dx formatting.

    Parameters
    ----------
    value: Any
        The value to test compatibility with.
    as_dataframe: bool
        Whether to return the results as a pandas DataFrame (if `True`),
        or as a dictionary (if `False`)
    """
    df = pd.DataFrame({"test": [value]})
    result = {}

    try:
        from jupyter_client.jsonutil import json_clean

        clean_json = json_clean(df.to_dict("records"))
        clean_json_value = clean_json[0]["test"]
        result["jupyter_client.jsonutil.json_clean"] = {
            "success": True,
            "type": type(clean_json_value),
            "value": clean_json_value,
        }
    except Exception as e:
        result["jupyter_client.jsonutil.json_clean"] = {
            "error": str(e),
            "success": False,
            "traceback": traceback.format_exc(),
        }

    if as_dataframe:
        return pd.DataFrame(result).transpose()
    return result

src.dx.datatypes.compatibility.test_db_write(value, as_dataframe=False)

Convenience function to test the compatibility of a given object inside a pandas DataFrame during registration with a duckdb connection, which is used during Datalink-enabled dataframe tracking for push-down filtering.

Parameters:

Name Type Description Default
value Any

The value to test compatibility with.

 required
as_dataframe bool

Whether to return the results as a pandas DataFrame (if True), or as a dictionary (if False)

 False
Source code in src/dx/datatypes/compatibility.py 
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
def test_db_write(value: Any, as_dataframe: bool = False) -> dict:
    """
    Convenience function to test the compatibility of a given object
    inside a pandas DataFrame during registration with a duckdb connection,
    which is used during Datalink-enabled dataframe tracking for
    push-down filtering.

    Parameters
    ----------
    value: Any
        The value to test compatibility with.
    as_dataframe: bool
        Whether to return the results as a pandas DataFrame (if `True`),
        or as a dictionary (if `False`)
    """
    from dx.utils.tracking import get_db_connection  # circular import

    df = pd.DataFrame({"test": [value]})
    result = {}

    db_connection = get_db_connection()
    try:
        db_connection.register("test", df)
        db_df = db_connection.execute("SELECT * FROM test").df()
        db_df_value = db_df.iloc[0]["test"]
        result["duckdb.conn.register"] = {
            "type": type(db_df_value),
            "success": True,
            "value": db_df_value,
        }
    except Exception as e:
        result["duckdb.conn.register"] = {
            "error": str(e),
            "success": False,
            "traceback": traceback.format_exc(),
        }

    if as_dataframe:
        return pd.DataFrame(result).transpose()
    return result

src.dx.datatypes.compatibility.test_dx_handling(value, as_dataframe=False)

Convenience function to test the compatibility of a given object inside a pandas DataFrame through the entire dx formatting and data type handling process.

Parameters:

Name Type Description Default
value Any

The value to test compatibility with.

 required
as_dataframe bool

Whether to return the results as a pandas DataFrame (if True), or as a dictionary (if False)

 False
Source code in src/dx/datatypes/compatibility.py 
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
def test_dx_handling(value: Any, as_dataframe: bool = False) -> dict:
    """
    Convenience function to test the compatibility of a given object
    inside a pandas DataFrame through the entire dx formatting
    and data type handling process.

    Parameters
    ----------
    value : Any
        The value to test compatibility with.
    as_dataframe : bool, optional
        Whether to return the results as a pandas DataFrame (if `True`),
        or as a dictionary (if `False`)
    """
    from dx.formatters.main import handle_format  # circular import

    df = pd.DataFrame({"test": [value]})
    result = {}

    try:
        payload, _ = handle_format(df, with_ipython_display=False)

        if settings.DISPLAY_MODE == "simple":
            dx_value = payload[settings.MEDIA_TYPE]["data"][0]["test"]
        if settings.DISPLAY_MODE == "enhanced":
            dx_value = payload[settings.MEDIA_TYPE]["data"][0][0]

        dx_schema_fields = payload[settings.MEDIA_TYPE]["schema"]["fields"]
        # should only be two fields here by default: `index` and `test`
        # but we wanted to run the entire formatting process, which doesn't need
        # an option to disable `index` from being included
        dx_schema_type = [field["type"] for field in dx_schema_fields if field["name"] == "test"][0]

        result["dx.handle_format"] = {
            "type": type(dx_value),
            "success": True,
            "value": dx_value,
            "schema_type": dx_schema_type,
        }
    except Exception as e:
        result["dx.handle_format"] = {
            "error": str(e),
            "success": False,
            "traceback": traceback.format_exc(),
        }

    if as_dataframe:
        return pd.DataFrame(result).transpose()
    return result