Develop Reference

iterate a dataframe

I'm trying to iterate a dataframe to call queries in mongodb from a list and save each query in a csv file. I have the connection with no errors, but when I iterate it just creates the frist file (0.csv) and I have an error for the second row of the dataframe.
This is my code:
sql = [
('tran','transactions',{"den": "00100002773060"}),
('tran','Data',{'name': 'john'}),
]
df = pd.DataFrame(sql, columns = ["database", "entity", "sql"])
for i in range(len(df)):
database = df.iloc[i]["database"]
entity=df.iloc[i]["entity"]
myquery=df.iloc[i]["sql"]
collection = client[database][entity]
try:
mydoc = list(collection.find(myquery))
if len(mydoc) > 0:
df = pd.DataFrame(mydoc)
df.pop("_id")
df.to_csv(str(i) + '.csv')
print("file saved")
except:
print("error on file")
and this the error
Traceback (most recent call last):
File "/home/r/Desktop/table_csv/entorno_virtual/lib/python3.8/site-packages/pandas/core/indexes/base.py", line 3629, in get_loc
return self._engine.get_loc(casted_key)
File "pandas/_libs/index.pyx", line 136, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/index.pyx", line 163, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/hashtable_class_helper.pxi", line 5198, in pandas._libs.hashtable.PyObjectHashTable.get_item
File "pandas/_libs/hashtable_class_helper.pxi", line 5206, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: 'database'
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "getSql.py", line 12, in <module>
database = df.iloc[i]["database"]
File "/home/r/Desktop/table_csv/entorno_virtual/lib/python3.8/site-packages/pandas/core/series.py", line 958, in __getitem__
return self._get_value(key)
File "/home/r/Desktop/table_csv/entorno_virtual/lib/python3.8/site-packages/pandas/core/series.py", line 1069, in _get_value
loc = self.index.get_loc(label)
File "/home/r/Desktop/table_csv/entorno_virtual/lib/python3.8/site-packages/pandas/core/indexes/base.py", line 3631, in get_loc
raise KeyError(key) from err
KeyError: 'database'

from what I can see here you are changing your df variable here
df = pd.DataFrame(mydoc)
probably just rename it

Getting 'KeyError' while trying to get matching values with two csv files

So I just tried making a basic 10 line movie recommendation system with a big ML project in mind. But It's only errors I'm getting while running this:
import pandas as pd
movies = pd.read_csv('movies.csv')
users = pd.read_csv('users.csv')
recommendations = {}
def recommend(users,movies):
for f in users['favouritegenre']:
genre = movies.query(f)['genre']
movie = movies.query(genre)['movie']
userid = users.query(f)['userid']
recommendations[userid]=movie
print(recommendations)
recommend(users,movies)
My movies csv file:
movie,ratings,genre
'toy story','8','family'
'john wick','7','action'
'a quite place','8','horror'
users csv file:
userid,age,favouritegenre
'1','16','family'
'2','49','action'
'3','10','horror'
and I get the error:
Traceback (most recent call last):
File "main.py", line 15, in <module>
recommend(users,movies)
File "main.py", line 9, in recommend
genre = movies.query(f)['genre']
File "C:\Users\user\AppData\Local\Programs\Python\Python38-32\lib\site-packages\pandas\core\frame.py", line 4114, in query
result = self.loc[res]
File "C:\Users\user\AppData\Local\Programs\Python\Python38-32\lib\site-packages\pandas\core\indexing.py", line 967, in __getitem__
return self._getitem_axis(maybe_callable, axis=axis)
File "C:\Users\user\AppData\Local\Programs\Python\Python38-32\lib\site-packages\pandas\core\indexing.py", line 1202, in _getitem_axis
return self._get_label(key, axis=axis)
File "C:\Users\user\AppData\Local\Programs\Python\Python38-32\lib\site-packages\pandas\core\indexing.py", line 1153, in _get_label
return self.obj.xs(label, axis=axis)
File "C:\Users\user\AppData\Local\Programs\Python\Python38-32\lib\site-packages\pandas\core\generic.py", line 3864, in xs
loc = index.get_loc(key)
File "C:\Users\user\AppData\Local\Programs\Python\Python38-32\lib\site-packages\pandas\core\indexes\range.py", line 389, in get_loc
raise KeyError(key)
KeyError: 'family'

IIUC, you can do
recommendations = (users.assign(movies=users['favouritegenre'].map(movies.groupby('genre')['movie'].agg(list)))
.set_index('userid')['movies'].to_dict())
print(recommendations)
{1: ['toy story'], 2: ['john wick'], 3: ['a quite place']}

Error shows up when using df.to_parquet("filename")

I want to save the data set as a parquet file, called power.parquet, and I use df.to_parquet(<filename>). But it gives me this errer "ValueError: Error converting column "Global_reactive_power" to bytes using encoding UTF8. Original error: bad argument type for built-in operation" And I installed the fastparquet package.
from fastparquet import write, ParquetFile
dat.to_parquet("power.parquet")
df_parquet = ParquetFile("power.parquet").to_pandas()
df_parquet.head() # Test your final value
`*Traceback (most recent call last):
File "/opt/anaconda3/lib/python3.9/site-packages/fastparquet/writer.py", line 259, in convert
out = array_encode_utf8(data)
File "fastparquet/speedups.pyx", line 50, in fastparquet.speedups.array_encode_utf8
TypeError: bad argument type for built-in operation
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/var/folders/4f/bm2th1p56tz4rq_zffc8g3940000gn/T/ipykernel_85477/3080656655.py", line 1, in <module>
dat.to_parquet("power.parquet", compression="GZIP")
File "/opt/anaconda3/lib/python3.9/site-packages/dask/dataframe/core.py", line 4560, in to_parquet
return to_parquet(self, path, *args, **kwargs)
File "/opt/anaconda3/lib/python3.9/site-packages/dask/dataframe/io/parquet/core.py", line 732, in to_parquet
return compute_as_if_collection(
File "/opt/anaconda3/lib/python3.9/site-packages/dask/base.py", line 315, in compute_as_if_collection
return schedule(dsk2, keys, **kwargs)
File "/opt/anaconda3/lib/python3.9/site-packages/dask/threaded.py", line 79, in get
results = get_async(
File "/opt/anaconda3/lib/python3.9/site-packages/dask/local.py", line 507, in get_async
raise_exception(exc, tb)
File "/opt/anaconda3/lib/python3.9/site-packages/dask/local.py", line 315, in reraise
raise exc
File "/opt/anaconda3/lib/python3.9/site-packages/dask/local.py", line 220, in execute_task
result = _execute_task(task, data)
File "/opt/anaconda3/lib/python3.9/site-packages/dask/core.py", line 119, in _execute_task
return func(*(_execute_task(a, cache) for a in args))
File "/opt/anaconda3/lib/python3.9/site-packages/dask/utils.py", line 35, in apply
return func(*args, **kwargs)
File "/opt/anaconda3/lib/python3.9/site-packages/dask/dataframe/io/parquet/fastparquet.py", line 1167, in write_partition
rg = make_part_file(
File "/opt/anaconda3/lib/python3.9/site-packages/fastparquet/writer.py", line 716, in make_part_file
rg = make_row_group(f, data, schema, compression=compression,
File "/opt/anaconda3/lib/python3.9/site-packages/fastparquet/writer.py", line 701, in make_row_group
chunk = write_column(f, coldata, column,
File "/opt/anaconda3/lib/python3.9/site-packages/fastparquet/writer.py", line 554, in write_column
repetition_data, definition_data, encode[encoding](data, selement), 8 * b'\x00'
File "/opt/anaconda3/lib/python3.9/site-packages/fastparquet/writer.py", line 354, in encode_plain
out = convert(data, se)
File "/opt/anaconda3/lib/python3.9/site-packages/fastparquet/writer.py", line 284, in convert
raise ValueError('Error converting column "%s" to bytes using '
ValueError: Error converting column "Global_reactive_power" to bytes using encoding UTF8. Original error: bad argument type for built-in operation
*
I tried by adding object_coding = "bytes".I want to solve this problem.

Pandas AttributeError: 'DataFrame' object has no attribute 'Timestamp'

so i want to get the monthly sum with my script but i always get an AttributeError, which i dont understand. The column Timestamp does indeed exist on my combined_csv. I know for sure that this line is causing the problem since i tested al of my other code before.
AttributeError: 'DataFrame' object has no attribute 'Timestamp'
I'll appreciate every kind of help i can get - thanks
import os
import glob
import pandas as pd
# set working directory
os.chdir("Path to CSVs")
# find all csv files in the folder
# use glob pattern matching -> extension = 'csv'
# save result in list -> all_filenames
extension = 'csv'
all_filenames = [i for i in glob.glob('*.{}'.format(extension))]
# print(all_filenames)
# combine all files in the list
combined_csv = pd.concat([pd.read_csv(f, sep=';') for f in all_filenames])
# Format CSV
# Transform Timestamp column into datetime
combined_csv['Timestamp'] = pd.to_datetime(combined_csv.Timestamp)
# Read out first entry of every day of every month
combined_csv = round(combined_csv.resample('D', on='Timestamp')['HtmDht_Energy'].agg(['first']))
# To get the yield of day i have to subtract day 2 HtmDht_Energy - day 1 HtmDht_Energy
combined_csv["dailyYield"] = combined_csv["first"] - combined_csv["first"].shift()
# combined_csv.reset_index()
# combined_csv.index.set_names(["year", "month"], inplace=True)
combined_csv["monthlySum"] = combined_csv.groupby([combined_csv.Timestamp.dt.year, combined_csv.Timestamp.dt.month]).sum()
Output of combined_csv.columns
Index(['Timestamp', 'teHst0101', 'teHst0102', 'teHst0103', 'teHst0104',
'teHst0105', 'teHst0106', 'teHst0107', 'teHst0201', 'teHst0202',
'teHst0203', 'teHst0204', 'teHst0301', 'teHst0302', 'teHst0303',
'teHst0304', 'teAmb', 'teSolFloHexHst', 'teSolRetHexHst',
'teSolCol0501', 'teSolCol1001', 'teSolCol1501', 'vfSol', 'prSolRetSuc',
'rdGlobalColAngle', 'gSolPump01_roActual', 'gSolPump02_roActual',
'gHstPump03_roActual', 'gHstPump04_roActual', 'gDhtPump06_roActual',
'gMB01_isOpened', 'gMB02_isOpened', 'gCV01_posActual',
'gCV02_posActual', 'HtmDht_Energy', 'HtmDht_Flow', 'HtmDht_Power',
'HtmDht_Volume', 'HtmDht_teFlow', 'HtmDht_teReturn', 'HtmHst_Energy',
'HtmHst_Flow', 'HtmHst_Power', 'HtmHst_Volume', 'HtmHst_teFlow',
'HtmHst_teReturn', 'teSolColDes', 'teHstFloDes'],
dtype='object')
Traceback:
When i select it with
combined_csv["monthlySum"] = combined_csv.groupby([combined_csv['Timestamp'].dt.year, combined_csv['Timestamp'].dt.month]).sum()
Traceback (most recent call last):
File "D:\Users\wink\PycharmProjects\csvToExcel\main.py", line 28, in <module>
combined_csv["monthlySum"] = combined_csv.groupby([combined_csv['Timestamp'].dt.year, combined_csv['Timestamp'].dt.month]).sum()
File "D:\Users\wink\PycharmProjects\csvToExcel\venv\lib\site-packages\pandas\core\frame.py", line 3024, in __getitem__
indexer = self.columns.get_loc(key)
File "D:\Users\wink\PycharmProjects\csvToExcel\venv\lib\site-packages\pandas\core\indexes\base.py", line 3082, in get_loc
raise KeyError(key) from err
KeyError: 'Timestamp'
traceback with mustafas solution
Traceback (most recent call last):
File "C:\Users\winklerm\PycharmProjects\csvToExcel\venv\lib\site-packages\pandas\core\frame.py", line 3862, in reindexer
value = value.reindex(self.index)._values
File "C:\Users\winklerm\PycharmProjects\csvToExcel\venv\lib\site-packages\pandas\util\_decorators.py", line 312, in wrapper
return func(*args, **kwargs)
File "C:\Users\winklerm\PycharmProjects\csvToExcel\venv\lib\site-packages\pandas\core\frame.py", line 4176, in reindex
return super().reindex(**kwargs)
File "C:\Users\winklerm\PycharmProjects\csvToExcel\venv\lib\site-packages\pandas\core\generic.py", line 4811, in reindex
return self._reindex_axes(
File "C:\Users\winklerm\PycharmProjects\csvToExcel\venv\lib\site-packages\pandas\core\frame.py", line 4022, in _reindex_axes
frame = frame._reindex_index(
File "C:\Users\winklerm\PycharmProjects\csvToExcel\venv\lib\site-packages\pandas\core\frame.py", line 4038, in _reindex_index
new_index, indexer = self.index.reindex(
File "C:\Users\winklerm\PycharmProjects\csvToExcel\venv\lib\site-packages\pandas\core\indexes\multi.py", line 2492, in reindex
target = MultiIndex.from_tuples(target)
File "C:\Users\winklerm\PycharmProjects\csvToExcel\venv\lib\site-packages\pandas\core\indexes\multi.py", line 175, in new_meth
return meth(self_or_cls, *args, **kwargs)
File "C:\Users\winklerm\PycharmProjects\csvToExcel\venv\lib\site-packages\pandas\core\indexes\multi.py", line 531, in from_tuples
arrays = list(lib.tuples_to_object_array(tuples).T)
File "pandas\_libs\lib.pyx", line 2527, in pandas._libs.lib.tuples_to_object_array
ValueError: Buffer dtype mismatch, expected 'Python object' but got 'long long'
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "C:\Users\winklerm\PycharmProjects\csvToExcel\main.py", line 28, in <module>
combined_csv["monthlySum"] = combined_csv.groupby([combined_csv.Timestamp.dt.year, combined_csv.Timestamp.dt.month]).sum()
File "C:\Users\winklerm\PycharmProjects\csvToExcel\venv\lib\site-packages\pandas\core\frame.py", line 3163, in __setitem__
self._set_item(key, value)
File "C:\Users\winklerm\PycharmProjects\csvToExcel\venv\lib\site-packages\pandas\core\frame.py", line 3242, in _set_item
value = self._sanitize_column(key, value)
File "C:\Users\winklerm\PycharmProjects\csvToExcel\venv\lib\site-packages\pandas\core\frame.py", line 3888, in _sanitize_column
value = reindexer(value).T
File "C:\Users\winklerm\PycharmProjects\csvToExcel\venv\lib\site-packages\pandas\core\frame.py", line 3870, in reindexer
raise TypeError(
TypeError: incompatible index of inserted column with frame index

This line makes the Timestamp column the index of the combined_csv:
combined_csv = round(combined_csv.resample('D', on='Timestamp')['HtmDht_Energy'].agg(['first']))
and therefore you get an error when you try to access .Timestamp.
Remedy is to reset_index, so instead of above line, you can try this:
combined_csv = round(combined_csv.resample('D', on='Timestamp')['HtmDht_Energy'].agg(['first'])).reset_index()
which will take the Timestamp column back into normal columns from the index and you can then access it.
Side note:
combined_csv["dailyYield"] = combined_csv["first"] - combined_csv["first"].shift()
is equivalent to
combined_csv["dailyYield"] = combined_csv["first"].diff()

raise KeyError(key) Python

I get this error when executing my code do you have an idea how to fix it? here is the image and the code of the first lines of my csv file, the file is too big to display it entirely. the code is complete. i try to display the points on a map with geoplotlib
enter image description here
import geoplotlib
import csv
import pandas as pd
data = pd.read_csv('E:\Projet de Memoir sur les tics/humdataAL.csv')
geoplotlib.dot(data)
geoplotlib.show()
It returns the following error:
Traceback (most recent call last):
File "C:\Users\nsama\PycharmProjects\pythonProject\amara_project\venv\lib\site-packages\geoplotlib\__init__.py", line 32, in _runapp
app.start()
File "C:\Users\nsama\PycharmProjects\pythonProject\amara_project\venv\lib\site-packages\geoplotlib\core.py", line 364, in start
self.proj.fit(BoundingBox.from_bboxes([l.bbox() for l in self.geoplotlib_config.layers]),
File "C:\Users\nsama\PycharmProjects\pythonProject\amara_project\venv\lib\site-packages\geoplotlib\core.py", line 364, in <listcomp>
self.proj.fit(BoundingBox.from_bboxes([l.bbox() for l in self.geoplotlib_config.layers]),
File "C:\Users\nsama\PycharmProjects\pythonProject\amara_project\venv\lib\site-packages\geoplotlib\layers.py", line 159, in bbox
return BoundingBox.from_points(lons=self.data['lon'], lats=self.data['lat'])
File "C:\Users\nsama\PycharmProjects\pythonProject\amara_project\venv\lib\site-packages\pandas\core\frame.py", line 3024, in __getitem__
indexer = self.columns.get_loc(key)
File "C:\Users\nsama\PycharmProjects\pythonProject\amara_project\venv\lib\site-packages\pandas\core\indexes\base.py", line 3082, in get_loc
raise KeyError(key) from err
KeyError: 'lon'

Your CSV doesn't meet geoplotlib specifications. In particular, all rows must have columns named lat and lon in dataset.