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

Creating a deltatime array in Python

I am new to python, so I decided to start a project to improve my skills. Therefore, I started trying this one on GeeksForGeeks. Now, I am having difficulty to append a deltaTime variable into an array. I tried a numpy array as well, but it did not worked out.
My code:
from matplotlib.ticker import Formatter
import pandas as pd
import matplotlib.pyplot as plt
import datetime
import numpy as np
from pandas._libs.tslibs import timestamps
birdData = pd.read_csv("bird_tracking.csv")
birdNames = pd.unique(birdData.bird_name)
#Pegando intervalo do tempo
timestamps = []
for i in range(len(birdData)):
timestamps.append(datetime.datetime.strptime(birdData.date_time.iloc[i][:-3], "%Y-%m-%d %H:%M:%S"))
birdData["timestamps"] = pd.Series(timestamps, index = birdData.index)
plt.figure(figsize=(7, 7))
for name in birdNames:
times = birdData.timestamps[birdData.bird_name == name]
elapsedTime = []
for time in times:
x = time-times[0]
#print(x)
elapsedTime.append(x)
plt.plot(np.array(elapsedTime)/datetime.timedelta(days=1), label = name)
plt.xlabel(" Observation ")
plt.ylabel(" Elapsed time (days) ")
plt.show()
The error that I am finding:
Traceback (most recent call last):
File "C:\Users\User\anaconda3\lib\site-packages\pandas\core\indexes\base.py", line 3080, in get_loc
return self._engine.get_loc(casted_key)
File "pandas\_libs\index.pyx", line 70, in pandas._libs.index.IndexEngine.get_loc
File "pandas\_libs\index.pyx", line 101, in pandas._libs.index.IndexEngine.get_loc
File "pandas\_libs\hashtable_class_helper.pxi", line 1625, in pandas._libs.hashtable.Int64HashTable.get_item
File "pandas\_libs\hashtable_class_helper.pxi", line 1632, in pandas._libs.hashtable.Int64HashTable.get_item
KeyError: 0
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "c:\Users\User\Documents\GitHub\TrackingBirdMigration\dataTime.py", line 24, in <module>
x = time-times[0]
File "C:\Users\User\anaconda3\lib\site-packages\pandas\core\series.py", line 853, in __getitem__
return self._get_value(key)
File "C:\Users\User\anaconda3\lib\site-packages\pandas\core\series.py", line 961, in _get_value
loc = self.index.get_loc(label)
File "C:\Users\User\anaconda3\lib\site-packages\pandas\core\indexes\base.py", line 3082, in get_loc
raise KeyError(key) from err
KeyError: 0
[Done] exited with code=1 in 8.313 seconds

KeyError(Key) when using append with defaultdict

I am getting the following error when I am trying to append to a dictionary using defaultdict(list). From my understanding, defaultdict is suppose to prevent a keyerror.
raise KeyError(key) from err
KeyError: 'id'
The following is my code:
weather_data = defaultdict(list)
m = len(_ids)
date = str(date.today())
i = 0
while i < m:
url = ("https://api.openweathermap.org/data/2.5/weather?id=%s&units=%s&appid=%s") %
(_ids.loc[i], 'imperial', weather_key)
payload = r.get(url).json()
payload_from_json = pd.json_normalize(payload)
weather_data[date].append(date)
weather_data['id'].append(payload_from_json['id'])
weather_data['weather'].append(payload_from_json['weather'])
weather_data['base'].append(payload_from_json['base'])
weather_data['visibility'].append(payload_from_json['visibility'])
weather_data['dt'].append(payload_from_json['dt'])
weather_data['name'].append(payload_from_json['name'])
weather_data['cod'].append(payload_from_json['cod'])
weather_data['coord.lon'].append(payload_from_json['coord.lon'])
weather_data['coord.lat'].append(payload_from_json['coord.lat'])
weather_data['main.temp'].append(payload_from_json['main.temp'])
weather_data['main.feels_like'].append(payload_from_json['main.feels_like'])
weather_data['main.temp_min'].append(payload_from_json['main.temp_min'])
weather_data['main.temp_max'].append(payload_from_json['main.temp_max'])
weather_data['main.pressure'].append(payload_from_json['main.pressure'])
weather_data['main.humidity'].append(payload_from_json['main.humidity'])
weather_data['wind.speed'].append(payload_from_json['wind.speed'])
weather_data['wind.deg'].append(payload_from_json['wind.deg'])
weather_data['clouds.all'].append(payload_from_json['clouds.all'])
weather_data['sys.type'].append(payload_from_json['sys.type'])
weather_data['sys.id'].append(payload_from_json['sys.id'])
weather_data['sys.country'].append(payload_from_json['sys.country'])
weather_data['sys.sunrise'].append(payload_from_json['sys.sunrise'])
weather_data['sys.sunset'].append(payload_from_json['sys.sunset'])
i = i + 1
print(weather_data)
Here is the traceback error - can someone tell me how to interpret this:
Traceback (most recent call last):
File "/opt/anaconda3/lib/python3.8/site-packages/pandas/core/indexes/base.py", line 2895, in get_loc
return self._engine.get_loc(casted_key)
File "pandas/_libs/index.pyx", line 70, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/index.pyx", line 101, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/hashtable_class_helper.pxi", line 1675, in pandas._libs.hashtable.PyObjectHashTable.get_item
File "pandas/_libs/hashtable_class_helper.pxi", line 1683, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: 'coord.lon'
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "main.py", line 40, in <module>
weather_data['coord.lon'].append(payload_from_json['coord.lon'])
File "/opt/anaconda3/lib/python3.8/site-packages/pandas/core/frame.py", line 2902, in __getitem__
indexer = self.columns.get_loc(key)
File "/opt/anaconda3/lib/python3.8/site-packages/pandas/core/indexes/base.py", line 2897, in get_loc
raise KeyError(key) from err

[EDIT]
your weather_data is your default dict, but payload_from_json not. So your error was raised by payload_from_json.
You can fix this by using get to access the key:
weather_data['id'].append(payload_from_json.get('id'))
if you dont want to include junk data, you can add some verifications before append:
if payload_from_json.get('id') is not None:
weather_data['id'].append(payload_from_json.get('id'))
Also, you can add some default value like this:
weather_data['id'].append(payload_from_json.get('id', 'missing'))
or
weather_data['id'].append(payload_from_json.get('id', ''))
or by default:
weather_data['id'].append(payload_from_json.get('id', None))
In your specific problem, this should work:
weather_data = defaultdict(list)
m = len(_ids)
date = str(date.today())
i = 0
while i < m:
url = ("https://api.openweathermap.org/data/2.5/weather?id=%s&units=%s&appid=%s") %
(_ids.loc[i], 'imperial', weather_key)
payload = r.get(url).json()
payload_from_json = pd.json_normalize(payload)
weather_data[date].append(date)
weather_data['id'].append(payload_from_json.get('id'))
weather_data['weather'].append(payload_from_json.get('weather'))
weather_data['base'].append(payload_from_json.get('base'))
weather_data['visibility'].append(payload_from_json.get('visibility'))
weather_data['dt'].append(payload_from_json.get('dt'))
weather_data['name'].append(payload_from_json.get('name'))
weather_data['cod'].append(payload_from_json.get('cod'))
weather_data['coord.lon'].append(payload_from_json.get('coord.lon'))
weather_data['coord.lat'].append(payload_from_json.get('coord.lat'))
weather_data['main.temp'].append(payload_from_json.get('main.temp'))
weather_data['main.feels_like'].append(payload_from_json.get('main.feels_like'))
weather_data['main.temp_min'].append(payload_from_json.get('main.temp_min'))
weather_data['main.temp_max'].append(payload_from_json.get('main.temp_max'))
weather_data['main.pressure'].append(payload_from_json.get('main.pressure'))
weather_data['main.humidity'].append(payload_from_json.get('main.humidity'))
weather_data['wind.speed'].append(payload_from_json.get('wind.speed'))
weather_data['wind.deg'].append(payload_from_json.get('wind.deg'))
weather_data['clouds.all'].append(payload_from_json.get('clouds.all'))
weather_data['sys.type'].append(payload_from_json.get('sys.type'))
weather_data['sys.id'].append(payload_from_json.get('sys.id'))
weather_data['sys.country'].append(payload_from_json.get('sys.country'))
weather_data['sys.sunrise'].append(payload_from_json.get('sys.sunrise'))
weather_data['sys.sunset'].append(payload_from_json.get('sys.sunset'))
i += 1

Key error message when calculating variables using pandas and yfinance

trying to calculate some variables from yfinance from the column df['Close'].
But im getting this error which i have not seen before. and heres are the code:
import os
import pandas as pd
import plotly.graph_objects as go
symbols = 'AAPL'
for filename in os.listdir('datasets/'):
#print(filename)
symbol = filename.split('.')[0]
#print(symbol)
df = pd.read_csv('datasets/{}'.format(filename))
if df.empty:
continue
df['20_sma'] = df['Close'].rolling(window=20).mean()
df['stddev'] = df['Close'].rolling(window=20).std()
df['lowerband'] = df['20_sma'] + (2* df['stddev'])
df['upperband'] = df['20_sma'] - (2* df['stddev'])
if symbol in symbols:
print(df)
and heres are the error message:
Traceback (most recent call last):
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pandas/core/indexes/base.py", line 2895, in get_loc
return self._engine.get_loc(casted_key)
File "pandas/_libs/index.pyx", line 70, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/index.pyx", line 101, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/hashtable_class_helper.pxi", line 1675, in pandas._libs.hashtable.PyObjectHashTable.get_item
File "pandas/_libs/hashtable_class_helper.pxi", line 1683, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: 'Close'
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/Users/Kit/Documents/TTM_squeezer/squeeze.py", line 16, in <module>
df['20_sma'] = df['Close'].rolling(window=20).mean()
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pandas/core/frame.py", line 2906, in __getitem__
indexer = self.columns.get_loc(key)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pandas/core/indexes/base.py", line 2897, in get_loc
raise KeyError(key) from err
KeyError: 'Close'
Seems like the 'Close' column has contributed to this error but i just cant figure out why?
Many thanks

turns out there was an error in the process where the local file was saved
case closed, thanks all

builtin keyerror while using pandas datareader to extract data

I'm using a loop to extract data by using pandas datareader, the first two loops are working properly.
But from the third loop, the code starts to return a builtin keyerror which is unexpected. i wonder since the first two loops are working properly, why from the third loop it starts to return error? and how to fix it?
import pandas as pd
import datetime as dt
import pandas_datareader as web
#====================================================
pd.set_option('display.max_columns', None)
pd.set_option('display.width', None)
pd.set_option('display.max_colwidth', -1)
#############
prev=15
endDate=dt.datetime.today().date()
sDate=endDate-pd.to_timedelta(prev,unit='d')
#############
def get_price(tickers): #input is a list or Series
result=pd.DataFrame()
for i in tickers:
df=pd.DataFrame()
df['Adj Close']=web.DataReader(i,'yahoo',sDate,endDate)['Adj Close']
df['MA']=df['Adj Close'].rolling(5).mean()
df.sort_values(ascending=False,inplace=True,by="Date")
df['Higher?']=df['Adj Close']>df['MA']
df['Higher?']=df['Higher?'].astype(int)
result['{}'.format(i)]=df['Higher?']
return result
#=============================================================================
base_url = "http://www.sectorspdr.com/sectorspdr/IDCO.Client.Spdrs.Holdings/Export/ExportExcel?symbol="
data = {
'Ticker' : [ 'XLC','XLY','XLP','XLE','XLF','XLV','XLI','XLB','XLRE','XLK','XLU' ]
, 'Name' : [ 'Communication Services','Consumer Discretionary','Consumer Staples','Energy','Financials','Health Care','Industrials','Materials','Real Estate','Technology','Utilities' ]
}
spdr_df = pd.DataFrame(data)
print(spdr_df)
for i, row in spdr_df.iterrows():
url = base_url + row['Ticker']
df_url = pd.read_excel(url)
header = df_url.iloc[0]
holdings_df = df_url[1:]
holdings_df.set_axis(header, axis='columns', inplace=True)
holdings_df=holdings_df['Symbol'].replace('.','-')
a=get_price(holdings_df)
print(a)
the errors are listed below:
a=get_price(holdings_df)
File "C:/Users/austi/Desktop/stock&trading/get etf holdings Main Version.py", line 25, in <module>
df['Adj Close']=web.DataReader(i,'yahoo',sDate,endDate)['Adj Close']
File "C:\Users\austi\Downloads\Python 3.6.3\Lib\site-packages\pandas\util\_decorators.py", line 214, in wrapper
return func(*args, **kwargs)
File "C:\Users\austi\Downloads\Python 3.6.3\Lib\site-packages\pandas_datareader\data.py", line 387, in DataReader
session=session,
File "C:\Users\austi\Downloads\Python 3.6.3\Lib\site-packages\pandas_datareader\base.py", line 251, in read
df = self._read_one_data(self.url, params=self._get_params(self.symbols))
File "C:\Users\austi\Downloads\Python 3.6.3\Lib\site-packages\pandas_datareader\yahoo\daily.py", line 165, in _read_one_data
prices["Date"] = to_datetime(to_datetime(prices["Date"], unit="s").dt.date)
File "C:\Users\austi\Downloads\Python 3.6.3\Lib\site-packages\pandas\core\frame.py", line 2800, in __getitem__
indexer = self.columns.get_loc(key)
File "C:\Users\austi\Downloads\Python 3.6.3\Lib\site-packages\pandas\core\indexes\base.py", line 2648, in get_loc
return self._engine.get_loc(self._maybe_cast_indexer(key))
File "C:\Users\austi\Downloads\Python 3.6.3\Lib\site-packages\pandas\_libs\index.cp36-win32.pyd", line 111, in pandas._libs.index.IndexEngine.get_loc
File "C:\Users\austi\Downloads\Python 3.6.3\Lib\site-packages\pandas\_libs\index.cp36-win32.pyd", line 138, in pandas._libs.index.IndexEngine.get_loc
File "C:\Users\austi\Downloads\Python 3.6.3\Lib\site-packages\pandas\_libs\hashtable.cp36-win32.pyd", line 1619, in pandas._libs.hashtable.PyObjectHashTable.get_item
Array of values of which unique will be calculated
File "C:\Users\austi\Downloads\Python 3.6.3\Lib\site-packages\pandas\_libs\hashtable.cp36-win32.pyd", line 1627, in pandas._libs.hashtable.PyObjectHashTable.get_item
builtins.KeyError: 'Date'```

For same tickers, there is no date column.
To catch the error and continue, try this code:
def get_price(tickers): #input is a list or Series
result=pd.DataFrame()
for i in tickers:
try:
df=pd.DataFrame()
df['Adj Close']=web.DataReader(i,'yahoo',sDate,endDate)['Adj Close']
df['MA']=df['Adj Close'].rolling(5).mean()
df.sort_values(ascending=False,inplace=True,by="Date") # sometimes error
df['Higher?']=df['Adj Close']>df['MA']
df['Higher?']=df['Higher?'].astype(int)
result['{}'.format(i)]=df['Higher?']
except Exception as ex: # no date column
print('Ticker', i, 'ERROR', ex)
print(df)
return result