python - 类型错误 : to_list_if_array() got an unexpected keyword argument 'convert_dtype'

Question

我正在尝试将一些数据从 google 工作表加载到 colab，将其转换为 Pandas 数据框，然后使用 Altair 对其进行绘制。但是我遇到了意外错误 TypeError: to_list_if_array() got an unexpected keyword argument 'convert_dtype'。

这是怎么回事？这是因为我将列转换为数字数据吗？我尝试删除转换但没有用。当我使用其中一个 altair 预制数据集绘制散点图时，它起作用了，所以它一定是数据集的问题。但是数据集中的所有数据类型及其条目似乎都是正确的。

# Import data from google sheet
from google.colab import auth
auth.authenticate_user()

import gspread
from oauth2client.client import GoogleCredentials

gc = gspread.authorize(GoogleCredentials.get_application_default())
worksheet = gc.open('My cool spreadsheet').sheet1

# get_all_values gives a list of rows.
rows = worksheet.get_all_values()

# Convert to a DataFrame
import pandas as pd
df = pd.DataFrame.from_records(rows)

# Use first row as column names
df = df.rename(columns=df.iloc[0])
df = df.drop(0)

# Encode some columns as numeric types
df['Victims'] = pd.to_numeric(df['Victims'], errors='coerce')
df['Starting year'] = pd.to_numeric(df['Starting year'], errors='coerce')

# Plot
import altair as alt

alt.Chart(df).mark_point().encode(
  x=alt.X('Starting year'),
  y=alt.Y('Victims'),
)

错误轨迹:

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/altair/vegalite/v4/api.py in to_dict(self, *args, **kwargs)
    361         copy = self.copy(deep=False)
    362         original_data = getattr(copy, "data", Undefined)
--> 363         copy.data = _prepare_data(original_data, context)
    364 
    365         if original_data is not Undefined:

12 frames
/usr/local/lib/python3.7/dist-packages/altair/vegalite/v4/api.py in _prepare_data(data, context)
     82     # convert dataframes  or objects with __geo_interface__ to dict
     83     if isinstance(data, pd.DataFrame) or hasattr(data, "__geo_interface__"):
---> 84         data = _pipe(data, data_transformers.get())
     85 
     86     # convert string input to a URLData

/usr/local/lib/python3.7/dist-packages/toolz/functoolz.py in pipe(data, *funcs)
    625     """
    626     for func in funcs:
--> 627         data = func(data)
    628     return data
    629 

/usr/local/lib/python3.7/dist-packages/toolz/functoolz.py in __call__(self, *args, **kwargs)
    301     def __call__(self, *args, **kwargs):
    302         try:
--> 303             return self._partial(*args, **kwargs)
    304         except TypeError as exc:
    305             if self._should_curry(args, kwargs, exc):

/usr/local/lib/python3.7/dist-packages/altair/vegalite/data.py in default_data_transformer(data, max_rows)
     17 @curried.curry
     18 def default_data_transformer(data, max_rows=5000):
---> 19     return curried.pipe(data, limit_rows(max_rows=max_rows), to_values)
     20 
     21 

/usr/local/lib/python3.7/dist-packages/toolz/functoolz.py in pipe(data, *funcs)
    625     """
    626     for func in funcs:
--> 627         data = func(data)
    628     return data
    629 

/usr/local/lib/python3.7/dist-packages/toolz/functoolz.py in __call__(self, *args, **kwargs)
    301     def __call__(self, *args, **kwargs):
    302         try:
--> 303             return self._partial(*args, **kwargs)
    304         except TypeError as exc:
    305             if self._should_curry(args, kwargs, exc):

/usr/local/lib/python3.7/dist-packages/altair/utils/data.py in to_values(data)
    147         return {"values": data}
    148     elif isinstance(data, pd.DataFrame):
--> 149         data = sanitize_dataframe(data)
    150         return {"values": data.to_dict(orient="records")}
    151     elif isinstance(data, dict):

/usr/local/lib/python3.7/dist-packages/altair/utils/core.py in sanitize_dataframe(df)
    346             # Convert numpy arrays saved as objects to lists
    347             # Arrays are not JSON serializable
--> 348             col = df[col_name].apply(to_list_if_array, convert_dtype=False)
    349             df[col_name] = col.where(col.notnull(), None)
    350     return df

/usr/local/lib/python3.7/dist-packages/pandas/core/frame.py in apply(self, func, axis, raw, result_type, args, **kwds)
   7550             kwds=kwds,
   7551         )
-> 7552         return op.get_result()
   7553 
   7554     def applymap(self, func) -> "DataFrame":

/usr/local/lib/python3.7/dist-packages/pandas/core/apply.py in get_result(self)
    183             return self.apply_raw()
    184 
--> 185         return self.apply_standard()
    186 
    187     def apply_empty_result(self):

/usr/local/lib/python3.7/dist-packages/pandas/core/apply.py in apply_standard(self)
    274 
    275     def apply_standard(self):
--> 276         results, res_index = self.apply_series_generator()
    277 
    278         # wrap results

/usr/local/lib/python3.7/dist-packages/pandas/core/apply.py in apply_series_generator(self)
    303                 for i, v in enumerate(series_gen):
    304                     # ignore SettingWithCopy here in case the user mutates
--> 305                     results[i] = self.f(v)
    306                     if isinstance(results[i], ABCSeries):
    307                         # If we have a view on v, we need to make a copy because

/usr/local/lib/python3.7/dist-packages/pandas/core/apply.py in f(x)
    112 
    113             def f(x):
--> 114                 return func(x, *args, **kwds)
    115 
    116         else:

TypeError: to_list_if_array() got an unexpected keyword argument 'convert_dtype'

正在加载的数据表是this one

Answer 1

以下对我来说效果很好:

import altair as alt
import pandas as pd


df = pd.read_csv('https://docs.google.com/spreadsheets/d/1ZSZF7iX8jDcgP_uMpgy6vaQagLXzXmg4dqZCG4h-sOc/export?format=csv#gid=0')

# Encode some columns as numeric types
df['Victims'] = pd.to_numeric(df['Victims'], errors='coerce')
df['Starting year'] = pd.to_numeric(df['Starting year'], errors='coerce')

# Plot

alt.Chart(df).mark_point().encode(
  x=alt.X('Starting year'),
  y=alt.Y('Victims'),
)