The little piece of code is giving me more trouble than necessary. I would appreciate any help if I could. Thank you in advance for taking a look at this for me.
I am trying to sum up the price and the volume from the previous 22 data points which I added a column named dtt that holds this value. The formula that I am trying to represent here is:
vamp = [sum(1, dtt) price * volume] / [sum(1,dtt) volume]
Here is my code
# Import necessary libraries
import numpy as np
import pandas as pd
import os
# Load SPY dataset
spy_data = pd.read_csv('SPY.csv', parse_dates=['Date'])
# Compute Daily Return
spy_data['daily_ret'] = (spy_data['Adj Close'] - (spy_data['Adj Close']).shift(1)) / ((spy_data['Adj Close']).shift(1)) * 100
spy_data['daily_ret'] = spy_data['daily_ret'].fillna(0.0)
# calculate Annualized Volatility
rsquare = (spy_data['daily_ret']) ** 2
spy_data['annualized_volatility']=(np.sqrt(rsquare.rolling(252).sum() / 251) * np.sqrt(252))
spy_data['annualized_volatility'] = spy_data['annualized_volatility'].fillna(0)
spy_shares = 889112600
# Calculate Days to Trade
spy_data['dtt'] = spy_shares / (spy_data['Volume'].rolling(22).sum()/22)
spy_data['dtt'] = spy_data['dtt'].fillna(1).astype(int)
# Calculate VWAP
#numerator is equal to the sum of the price * volume of the latest DTT
numerator = spy_data.loc[0:spy_data['dtt'], 'Adj Close'].sum()#*spy_data.loc[0:spy_data['dtt'], 'Volume']
#denominator = spy_data.loc[0:spy_data['dtt'], 'Volume']
#spy_data['vwap'] = numerator / denominator
print(spy_data)
I commented out the other lines because I was trying to problem solve it one step at a time. The price column that I need is the Adj Close.
No matter what I try in terms of slicing I keep getting an error. This is the current one:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-68-ade975138e12> in <module>
7 # Calculate VWAP
8 #numerator is equal to the sum of the price * volume of the latest DTT
----> 9 numerator = spy_data.loc[0:spy_data['dtt']].sum()#*spy_data[0:spy_data['dtt'], 'volume']
10 #denominator = spy_data.loc[0:spy_data['dtt'], 'Volume']
11 #spy_data['vwap'] = numerator / denominator
~/.local/lib/python3.6/site-packages/pandas/core/indexing.py in __getitem__(self, key)
1408
1409 maybe_callable = com.apply_if_callable(key, self.obj)
-> 1410 return self._getitem_axis(maybe_callable, axis=axis)
1411
1412 def _is_scalar_access(self, key: Tuple):
~/.local/lib/python3.6/site-packages/pandas/core/indexing.py in _getitem_axis(self, key, axis)
1770 if isinstance(key, slice):
1771 self._validate_key(key, axis)
-> 1772 return self._get_slice_axis(key, axis=axis)
1773 elif com.is_bool_indexer(key):
1774 return self._getbool_axis(key, axis=axis)
~/.local/lib/python3.6/site-packages/pandas/core/indexing.py in _get_slice_axis(self, slice_obj, axis)
1438 labels = obj._get_axis(axis)
1439 indexer = labels.slice_indexer(
-> 1440 slice_obj.start, slice_obj.stop, slice_obj.step, kind=self.name
1441 )
1442
~/.local/lib/python3.6/site-packages/pandas/core/indexes/base.py in slice_indexer(self, start, end, step, kind)
5025 slice(1, 3)
5026 """
-> 5027 start_slice, end_slice = self.slice_locs(start, end, step=step, kind=kind)
5028
5029 # return a slice
~/.local/lib/python3.6/site-packages/pandas/core/indexes/base.py in slice_locs(self, start, end, step, kind)
5245 end_slice = None
5246 if end is not None:
-> 5247 end_slice = self.get_slice_bound(end, "right", kind)
5248 if end_slice is None:
5249 end_slice = len(self)
~/.local/lib/python3.6/site-packages/pandas/core/indexes/base.py in get_slice_bound(self, label, side, kind)
5155 # we need to look up the label
5156 try:
-> 5157 slc = self.get_loc(label)
5158 except KeyError as err:
5159 try:
~/.local/lib/python3.6/site-packages/pandas/core/indexes/range.py in get_loc(self, key, method, tolerance)
377 except ValueError:
378 raise KeyError(key)
--> 379 return super().get_loc(key, method=method, tolerance=tolerance)
380
381 #Appender(_index_shared_docs["get_indexer"])
~/.local/lib/python3.6/site-packages/pandas/core/indexes/base.py in get_loc(self, key, method, tolerance)
2888 )
2889 try:
-> 2890 return self._engine.get_loc(key)
2891 except KeyError:
2892 return self._engine.get_loc(self._maybe_cast_indexer(key))
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()
TypeError: '0 1
1 1
2 1
3 1
4 1
..
4694 9
4695 9
4696 10
4697 10
4698 11
Name: dtt, Length: 4699, dtype: int64' is an invalid key
Related
I have data, which has 2 input columns and 42 output columns. Here is what my code looks like:
data_columns=["value","average"]
prediction_columns=[]
for i in range(43):
prediction_columns.append("s"+str(i))
from keras.preprocessing.sequence import TimeseriesGenerator
n_input = 24*4 #how many samples/rows/timesteps to look in the past in order to forecast the next sample
n_features= len(prediction_columns)#X_train.shape[1] # how many predictors/Xs/features we have to predict y
b_size = 7 # Number of timeseries samples in each batch
generator = TimeseriesGenerator(columns[data_columns], columns[prediction_columns], length=n_input, batch_size=b_size)
print(generator[0][0].shape)
This fails with following:
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
File /usr/lib/python3.10/site-packages/pandas/core/indexes/base.py:3621, in Index.get_loc(self, key, method, tolerance)
3620 try:
-> 3621 return self._engine.get_loc(casted_key)
3622 except KeyError as err:
File /usr/lib/python3.10/site-packages/pandas/_libs/index.pyx:136, in pandas._libs.index.IndexEngine.get_loc()
File /usr/lib/python3.10/site-packages/pandas/_libs/index.pyx:163, in pandas._libs.index.IndexEngine.get_loc()
File pandas/_libs/hashtable_class_helper.pxi:5198, in pandas._libs.hashtable.PyObjectHashTable.get_item()
File pandas/_libs/hashtable_class_helper.pxi:5206, in pandas._libs.hashtable.PyObjectHashTable.get_item()
KeyError: 96
The above exception was the direct cause of the following exception:
KeyError Traceback (most recent call last)
Input In [38], in <cell line: 8>()
5 b_size = 7 # Number of timeseries samples in each batch
6 generator = TimeseriesGenerator(columns[data_columns], columns[prediction_columns], length=n_input, batch_size=b_size)
----> 8 print(generator[0][0].shape)
File /usr/lib/python3.10/site-packages/keras/preprocessing/sequence.py:176, in __getitem__(self, index)
172 rows = np.random.randint(
173 self.start_index, self.end_index + 1, size=self.batch_size
174 )
175 else:
--> 176 i = self.start_index + self.batch_size * self.stride * index
177 rows = np.arange(
178 i,
179 min(i + self.batch_size * self.stride, self.end_index + 1),
180 self.stride,
181 )
183 samples = np.array(
184 [
185 self.data[row - self.length : row : self.sampling_rate]
186 for row in rows
187 ]
188 )
File /usr/lib/python3.10/site-packages/keras/preprocessing/sequence.py:176, in <listcomp>(.0)
172 rows = np.random.randint(
173 self.start_index, self.end_index + 1, size=self.batch_size
174 )
175 else:
--> 176 i = self.start_index + self.batch_size * self.stride * index
177 rows = np.arange(
178 i,
179 min(i + self.batch_size * self.stride, self.end_index + 1),
180 self.stride,
181 )
183 samples = np.array(
184 [
185 self.data[row - self.length : row : self.sampling_rate]
186 for row in rows
187 ]
188 )
File /usr/lib/python3.10/site-packages/pandas/core/frame.py:3505, in DataFrame.__getitem__(self, key)
3503 if self.columns.nlevels > 1:
3504 return self._getitem_multilevel(key)
-> 3505 indexer = self.columns.get_loc(key)
3506 if is_integer(indexer):
3507 indexer = [indexer]
File /usr/lib/python3.10/site-packages/pandas/core/indexes/base.py:3623, in Index.get_loc(self, key, method, tolerance)
3621 return self._engine.get_loc(casted_key)
3622 except KeyError as err:
-> 3623 raise KeyError(key) from err
3624 except TypeError:
3625 # If we have a listlike key, _check_indexing_error will raise
3626 # InvalidIndexError. Otherwise we fall through and re-raise
3627 # the TypeError.
3628 self._check_indexing_error(key)
KeyError: 96
I thought that maybe I'm providing invalid column names, but both columns[data_columns].head() and columns[prediction_columns].head() execute without issues
Columns shape is (42749, 45)
What could be the source of the problem?
Problem went away after I converted dataframes to numpy
generator = TimeseriesGenerator(work[data_columns].to_numpy(), work[prediction_columns].to_numpy(), length=n_input, batch_size=b_size)
Could someone tell me what non-printable character I have in my code that makes python not recognize the columns names in my dataframe? :
import pandas as pd
data_olymp = pd.read_csv("Olympics_data.csv", sep=";")
Here is the Traceback of the error when I try to group by teamname :
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
<ipython-input-103-ae95f10f5210> in <module>
30 # print(type(réponse1))
31 # print(len(winter_games_bronze_won))
---> 32 print(data_olymp.loc[" winter_games_bronze_won"] == 9)
~\anaconda3\lib\site-packages\pandas\core\indexing.py in __getitem__(self, key)
893
894 maybe_callable = com.apply_if_callable(key, self.obj)
--> 895 return self._getitem_axis(maybe_callable, axis=axis)
896
897 def _is_scalar_access(self, key: Tuple):
~\anaconda3\lib\site-packages\pandas\core\indexing.py in _getitem_axis(self, key, axis)
1122 # fall thru to straight lookup
1123 self._validate_key(key, axis)
-> 1124 return self._get_label(key, axis=axis)
1125
1126 def _get_slice_axis(self, slice_obj: slice, axis: int):
~\anaconda3\lib\site-packages\pandas\core\indexing.py in _get_label(self, label, axis)
1071 def _get_label(self, label, axis: int):
1072 # GH#5667 this will fail if the label is not present in the axis.
-> 1073 return self.obj.xs(label, axis=axis)
1074
1075 def _handle_lowerdim_multi_index_axis0(self, tup: Tuple):
~\anaconda3\lib\site-packages\pandas\core\generic.py in xs(self, key, axis, level, drop_level)
3737 raise TypeError(f"Expected label or tuple of labels, got {key}") from e
3738 else:
-> 3739 loc = index.get_loc(key)
3740
3741 if isinstance(loc, np.ndarray):
~\anaconda3\lib\site-packages\pandas\core\indexes\range.py in get_loc(self, key, method, tolerance)
352 except ValueError as err:
353 raise KeyError(key) from err
--> 354 raise KeyError(key)
355 return super().get_loc(key, method=method, tolerance=tolerance)
356
KeyError: ' winter_games_bronze_won'
The file looks like that :
team_name; summer_games_played; summer_games_gold_won; summer_games_silver_won; summer_games_bronze_won; summer_games_medals_won; winter_games_played; winter_games_gold_won; winter_games_silver_won; winter_games_bronze_won; winter_games_medals_won; total_games_played
Canada (CAN);13;0;0;2;2;0;0;0;0;0;13
United States (USA);12;5;2;8;15;3;0;0;0;0;15
Russia (RUS);23;18;24;28;70;18;0;0;0;0;41
Key errors are raised when you are trying to access a key that is not in a dictionary. While working Pandas, it is about the same thing. .loc is trying to locate a key value that is not found in the data frame.
Looking at your code and the traceback error, my assumption is that because you are trying to look up winter_games_bronze_won (with the spaces at the beginning), you are getting the error. Try removing the spaces before winter_games_bronze_won and see what happens.
I have a panda dataframe and want to extract data by date.
If i use the loc() funktion with the date like
data_today = data.loc["2020-07-20"]
it will work and show the right data. But if I use a datetime it wont work.
import datetime as dt
from datetime import datetime , timedelta
date_today = dt.date.today() - dt.timedelta(days=5)
print(date_today)
data_today = data.loc["date_today"]
data_today
If I print date_today the format is the format of the DataFrame "2020-07-20" for example.
Thanks for the Help
Here the full code and errormessage
import datetime as dt
from datetime import datetime , timedelta
data = pd.read_csv("https://covid.ourworldindata.org/data/owid-covid-data.csv" , index_col = "date")
data.head()
date_today = dt.date.today() - dt.timedelta(days=5)
print(date_today)
data_today = data.loc["date_today"]
data_today
and the error
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
~\anaconda3\lib\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance)
2645 try:
-> 2646 return self._engine.get_loc(key)
2647 except KeyError:
pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas\_libs\index.pyx in pandas._libs.index.IndexEngine._get_loc_duplicates()
pandas\_libs\index.pyx in pandas._libs.index.IndexEngine._maybe_get_bool_indexer()
KeyError: 'date_today'
During handling of the above exception, another exception occurred:
KeyError Traceback (most recent call last)
<ipython-input-179-6abf305e8190> in <module>
5 print(date_today)
6
----> 7 data_today = data.loc["date_today"]
8 data_today
~\anaconda3\lib\site-packages\pandas\core\indexing.py in __getitem__(self, key)
1765
1766 maybe_callable = com.apply_if_callable(key, self.obj)
-> 1767 return self._getitem_axis(maybe_callable, axis=axis)
1768
1769 def _is_scalar_access(self, key: Tuple):
~\anaconda3\lib\site-packages\pandas\core\indexing.py in _getitem_axis(self, key, axis)
1962 # fall thru to straight lookup
1963 self._validate_key(key, axis)
-> 1964 return self._get_label(key, axis=axis)
1965
1966
~\anaconda3\lib\site-packages\pandas\core\indexing.py in _get_label(self, label, axis)
622 raise IndexingError("no slices here, handle elsewhere")
623
--> 624 return self.obj._xs(label, axis=axis)
625
626 def _get_loc(self, key: int, axis: int):
~\anaconda3\lib\site-packages\pandas\core\generic.py in xs(self, key, axis, level, drop_level)
3535 loc, new_index = self.index.get_loc_level(key, drop_level=drop_level)
3536 else:
-> 3537 loc = self.index.get_loc(key)
3538
3539 if isinstance(loc, np.ndarray):
~\anaconda3\lib\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance)
2646 return self._engine.get_loc(key)
2647 except KeyError:
-> 2648 return self._engine.get_loc(self._maybe_cast_indexer(key))
2649 indexer = self.get_indexer([key], method=method, tolerance=tolerance)
2650 if indexer.ndim > 1 or indexer.size > 1:
pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas\_libs\index.pyx in pandas._libs.index.IndexEngine._get_loc_duplicates()
pandas\_libs\index.pyx in pandas._libs.index.IndexEngine._maybe_get_bool_indexer()
KeyError: 'date_today'
Your code is mostly fine. You need to convert the index to date, and also use date_today as a variable rather than a string:
from datetime import datetime , timedelta
data = pd.read_csv("https://covid.ourworldindata.org/data/owid-covid-data.csv" , index_col = "date")
data.index = pd.to_datetime(data.index)
date_today = dt.date.today() - dt.timedelta(days=5)
data_today = data.loc[date_today]
print(data_today.head())
The output is:
iso_code continent location total_cases new_cases total_deaths new_deaths total_cases_per_million new_cases_per_million total_deaths_per_million ... aged_70_older \
date ...
2020-07-21 AFG Asia Afghanistan 35615.0 140.0 1186.0 5.0 914.886 3.596 30.466 ... 1.337
2020-07-21 ALB Europe Albania 4171.0 81.0 113.0 1.0 1449.371 28.147 39.266 ... 8.643
...
Your code should work fine, you just need to format date_today properly.
data.loc[date_today.strftime("%Y-%m-%d")]
I have 400 columns and I am trying to do min-max normalization (row-wise). For the first 200 points I want to do min-max normalization and scale it between 0 and 500 and do the same for the next two hundred points but scale it between 0 and 10.
import pandas as pd
import numpy as np
df = pd.DataFrame(np.random.randint(500,1000,size=(5, 400)))
def normalize(ds,value):
normalizedds = []
normalizedds.extend((ds[:value] - np.min(ds[:value])) / np.max(ds[:value] - np.min(ds[:value])) * 500)
normalizedds.extend(ds[value:value*2] / np.max(ds[value:value*2]) * 10)
return normalizedds
normalizeddsList = pd.DataFrame.from_records(df.apply(normalize, value=200, axis=1))
I get the following error!
ValueError Traceback (most recent call last)
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\indexes\base.py in get_slice_bound(self, label, side, kind)
5166 try:
-> 5167 return self._searchsorted_monotonic(label, side)
5168 except ValueError:
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\indexes\base.py in _searchsorted_monotonic(self, label, side)
5127
-> 5128 raise ValueError("index must be monotonic increasing or decreasing")
5129
ValueError: index must be monotonic increasing or decreasing
During handling of the above exception, another exception occurred:
KeyError Traceback (most recent call last)
in
----> 1 scaledCardList = pd.DataFrame.from_records(originalCardList.apply(scale, pointCount=200, axis=1))
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\frame.py in apply(self, func, axis, broadcast, raw, reduce, result_type, args, **kwds)
6926 kwds=kwds,
6927 )
-> 6928 return op.get_result()
6929
6930 def applymap(self, func):
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\apply.py in get_result(self)
184 return self.apply_raw()
185
--> 186 return self.apply_standard()
187
188 def apply_empty_result(self):
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\apply.py in apply_standard(self)
290
291 # compute the result using the series generator
--> 292 self.apply_series_generator()
293
294 # wrap results
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\apply.py in apply_series_generator(self)
319 try:
320 for i, v in enumerate(series_gen):
--> 321 results[i] = self.f(v)
322 keys.append(v.name)
323 except Exception as e:
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\apply.py in f(x)
110
111 def f(x):
--> 112 return func(x, *args, **kwds)
113
114 else:
in scale(card, pointCount)
1 def scale(card, pointCount):
2 scaledCard = []
----> 3 scaledCard.extend((card[:pointCount] - np.min(card[:pointCount])) / np.max(card[:pointCount] - np.min(card[:pointCount])) * 10000)
4 scaledCard.extend(card[pointCount:pointCount*2] / np.max(card[pointCount:pointCount*2]) * 100)
5 return scaledCard
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\series.py in getitem(self, key)
1111 key = check_bool_indexer(self.index, key)
1112
-> 1113 return self._get_with(key)
1114
1115 def _get_with(self, key):
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\series.py in _get_with(self, key)
1116 # other: fancy integer or otherwise
1117 if isinstance(key, slice):
-> 1118 indexer = self.index._convert_slice_indexer(key, kind="getitem")
1119 return self._get_values(indexer)
1120 elif isinstance(key, ABCDataFrame):
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\indexes\numeric.py in _convert_slice_indexer(self, key, kind)
395
396 # translate to locations
--> 397 return self.slice_indexer(key.start, key.stop, key.step, kind=kind)
398
399 def _format_native_types(
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\indexes\base.py in slice_indexer(self, start, end, step, kind)
5032 slice(1, 3)
5033 """
-> 5034 start_slice, end_slice = self.slice_locs(start, end, step=step, kind=kind)
5035
5036 # return a slice
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\indexes\base.py in slice_locs(self, start, end, step, kind)
5252 end_slice = None
5253 if end is not None:
-> 5254 end_slice = self.get_slice_bound(end, "right", kind)
5255 if end_slice is None:
5256 end_slice = len(self)
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\indexes\base.py in get_slice_bound(self, label, side, kind)
5168 except ValueError:
5169 # raise the original KeyError
-> 5170 raise err
5171
5172 if isinstance(slc, np.ndarray):
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\indexes\base.py in get_slice_bound(self, label, side, kind)
5162 # we need to look up the label
5163 try:
-> 5164 slc = self.get_loc(label)
5165 except KeyError as err:
5166 try:
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\indexes\numeric.py in get_loc(self, key, method, tolerance)
477 except (TypeError, NotImplementedError):
478 pass
--> 479 return super().get_loc(key, method=method, tolerance=tolerance)
480
481 #cache_readonly
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance)
2897 return self._engine.get_loc(key)
2898 except KeyError:
-> 2899 return self._engine.get_loc(self._maybe_cast_indexer(key))
2900 indexer = self.get_indexer([key], method=method, tolerance=tolerance)
2901 if indexer.ndim > 1 or indexer.size > 1:
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.Float64HashTable.get_item()
pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.Float64HashTable.get_item()
KeyError: (200.0, 'occurred at index 0')
I get an error when trying to create a Facet Grid with Seaborn. I have 3 categorical variables: Gender, Day of the Week, Color. I want to understand the direct correlation of all values within each category to each other.
Gender: Female, Male
Day of the Week: Mo,Tue,Wed,Thu,Fri,Sat,Sun
Color:Red, Green.
g = sns.FacetGrid(tips, col="Gender", row="Color")
g = g.map(plt.hist, "Day of the Week")
display()
Get an error:
KeyError-Traceback (most recent call last)
<command-206114> in <module>()
2 tips = sns.load_dataset("tips")
3
----> 4 g = sns.FacetGrid(tips, col="Gender", row="Color")
5 g = g.map(plt.hist, "Day of the week")
6 display()
/databricks/python/lib/python3.5/site-packages/seaborn/axisgrid.py in __init__(self, data, row, col, hue, col_wrap, sharex, sharey, size, aspect, palette, row_order, col_order, hue_order, hue_kws, dropna, legend_out, despine, margin_titles, xlim, ylim, subplot_kws, gridspec_kws)
240 row_names = []
241 else:
--> 242 row_names = utils.categorical_order(data[row], row_order)
243
244 if col is None:
/databricks/python/lib/python3.5/site-packages/pandas/core/frame.py in __getitem__(self, key)
2057 return self._getitem_multilevel(key)
2058 else:
-> 2059 return self._getitem_column(key)
2060
2061 def _getitem_column(self, key):
/databricks/python/lib/python3.5/site-packages/pandas/core/frame.py in _getitem_column(self, key)
2064 # get column
2065 if self.columns.is_unique:
-> 2066 return self._get_item_cache(key)
2067
2068 # duplicate columns & possible reduce dimensionality
/databricks/python/lib/python3.5/site-packages/pandas/core/generic.py in _get_item_cache(self, item)
1384 res = cache.get(item)
1385 if res is None:
-> 1386 values = self._data.get(item)
1387 res = self._box_item_values(item, values)
1388 cache[item] = res
/databricks/python/lib/python3.5/site-packages/pandas/core/internals.py in get(self, item, fastpath)
3541
3542 if not isnull(item):
-> 3543 loc = self.items.get_loc(item)
3544 else:
3545 indexer = np.arange(len(self.items))[isnull(self.items)]
/databricks/python/lib/python3.5/site-packages/pandas/indexes/base.py in get_loc(self, key, method, tolerance)
2134 return self._engine.get_loc(key)
2135 except KeyError:
-> 2136 return self._engine.get_loc(self._maybe_cast_indexer(key))
2137
2138 indexer = self.get_indexer([key], method=method, tolerance=tolerance)
KeyError: 'Color'
Does anybody know why this is?
The variable "Color" is the issue here. It could me misspelled . and if you are plotting two categorical varaibles try using a Bar Chart .