Get excel column into a variable - python

I want to move some xls data into json. I can't just use a ready solution, since this is a bit of a special case.
Here's the excel
Here's the code:
import pandas
xl = pandas.ExcelFile("./data/file.xlsx")
df = xl.parse("2")
x = df["XX"][0]
print(x)
# writing to file
text_file = open("json_files/Output.json", "w")
# text_file.write(json_str)
text_file.close()
Here's the error I'm getting:
Traceback (most recent call last):
File "C:\Users\aironsid\Documents\Capgemini\Excel_to_Json\venv\lib\site-packages\pandas\core\indexes\base.py", line 2646, in get_loc
return self._engine.get_loc(key)
File "pandas\_libs\index.pyx", line 111, in pandas._libs.index.IndexEngine.get_loc
File "pandas\_libs\index.pyx", line 138, in pandas._libs.index.IndexEngine.get_loc
File "pandas\_libs\hashtable_class_helper.pxi", line 1619, in pandas._libs.hashtable.PyObjectHashTable.get_item
File "pandas\_libs\hashtable_class_helper.pxi", line 1627, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: 'XX'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "excelToJson.py", line 5, in <module>
x = df["XX"][0]
File "C:\Users\aironsid\Documents\Capgemini\Excel_to_Json\venv\lib\site-packages\pandas\core\frame.py", line 2800, in __getitem__
indexer = self.columns.get_loc(key)
File "C:\Users\aironsid\Documents\Capgemini\Excel_to_Json\venv\lib\site-packages\pandas\core\indexes\base.py", line 2648, in get_loc
return self._engine.get_loc(self._maybe_cast_indexer(key))
File "pandas\_libs\index.pyx", line 111, in pandas._libs.index.IndexEngine.get_loc
File "pandas\_libs\index.pyx", line 138, in pandas._libs.index.IndexEngine.get_loc
File "pandas\_libs\hashtable_class_helper.pxi", line 1619, in pandas._libs.hashtable.PyObjectHashTable.get_item
File "pandas\_libs\hashtable_class_helper.pxi", line 1627, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: 'XX'
It seems to not be able to find the column name.
I'm using this video as reference
import pandas
xl = pandas.ExcelFile("file.xlsx")
# df = xl.parse("Text")
# print(df.columns)
# # x = df["XX"][0]
# # print(x)
df = pandas.Dataframe(xl)
print(df.columns)
# if you can see the columns
print(df["XX"])
# if this is success
dictionary = {"XX": list(df["XX"])}
# writing to file
text_file = open("json_files/Output.json", "w")
# text_file.write(json_str)
text_file.close()

please try this
df = pd.Dataframe(xl)
print(df.columns)
# if you can see the columns
print(df["XX"])
# if this is success
dictionary = {"XX": list(df["XX"])}

As mentioned in comments, you need to translate the starting point of A1 to B7 in your case. This can be achieved with the "skiprows" parameter of pandas.ExcelFile.parse and the index_col parameter:
import pandas
xl = pandas.ExcelFile("path\to\your\file.xlsx")
df = xl.parse("YourSheetName",index_col=1,skiprows=7)
For more documentation/parameters see pandas docs

Related

Read csv; replace values and save on csv

I have a csv file and I want to modify the first column by removing all "-".
After that, I want to save the changes in that same first column.
import pandas as pd
clean_order = pd.read_csv('C:/Users/(...)/Page_Clean_test.csv', 'w+', delimiter=';', skiprows=0, low_memory=False)
clean_order.loc[clean_order['web_scraper_order'].fillna('').str.replace('-', ''), 'web_scraper_order']
clean_order.to_csv('C:/Users/(...)/Page_Clean_test.csv', index=False)
Error:
File "C:\Users\suiso\PycharmProjects\Teste_SA\venv\lib\site-packages\pandas\core\indexes\base.py", line 2889, 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 97, 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: 'web_scraper_order'
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "C:/Users/suiso/PycharmProjects/Teste_SA/Clean Data/Dataframe_comments.py", line 21, in <module>
clean_order.loc[clean_order['web_scraper_order'].fillna('').str.replace('-', ''), 'web_scraper_order']
File "C:\Users\suiso\PycharmProjects\Teste_SA\venv\lib\site-packages\pandas\core\frame.py", line 2899, in __getitem__
indexer = self.columns.get_loc(key)
File "C:\Users\suiso\PycharmProjects\Teste_SA\venv\lib\site-packages\pandas\core\indexes\base.py", line 2891, in get_loc
raise KeyError(key) from err
KeyError: 'web_scraper_order'
Try changing:
clean_order.loc[clean_order['web_scraper_order'].fillna('').str.replace('-', ''), 'web_scraper_order']
To:
clean_order = clean_order[clean_order.loc['web_scraper_order'].fillna('').str.replace('-', '')]
you may use
clean_order['web_scraper_order']=clean_order['web_scraper_order'].str.replace('-','')
clean_order.to_csv('filename.csv',index=Flase)

Python Pandas: Why can't I convert 'Time' to to_datetime? Will not recognize time

Time data looks like this: Time
20:15:00.0
20:16:00.0
20:17:00.0
20:18:00.0
20:19:00.0
20:20:00.0
20:21:00.0
20:22:00.0
20:23:00.0
20:24:00.0
data: https://imgur.com/a/LQIjHGt)
Python recognizes these as:
Date object
**Time** **object**
Open float64
High float64
Low float64
Last float64
I've tried to import data like this:
hour
df = pd.read_csv('ES_1min_2012_vwap_va.txt', sep=",", nrows=1000, parse_dates=True);
df['Time'] = pd.to_datetime(df['Time'])
**ERROR**:
runfile('C:/Users/user/Desktop/Trading/Main/historical data/Index/ES/Intraday Volatility by VIX.py', wdir='C:/Users/user/Desktop/Trading/Main/historical data/Index/ES')
Traceback (most recent call last):
File "C:\Users\user\miniconda3\lib\site-packages\pandas\core\indexes\base.py", line 2646, in get_loc
return self._engine.get_loc(key)
File "pandas\_libs\index.pyx", line 111, in pandas._libs.index.IndexEngine.get_loc
File "pandas\_libs\index.pyx", line 138, in pandas._libs.index.IndexEngine.get_loc
File "pandas\_libs\hashtable_class_helper.pxi", line 1619, in pandas._libs.hashtable.PyObjectHashTable.get_item
File "pandas\_libs\hashtable_class_helper.pxi", line 1627, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: 'Time'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\Users\user\Desktop\Trading\Main\historical data\Index\ES\Intraday Volatility by VIX.py", line 18, in <module>
df['Time'] = pd.to_datetime(df['Time'], errors='ignore')
File "C:\Users\user\miniconda3\lib\site-packages\pandas\core\frame.py", line 2800, in __getitem__
indexer = self.columns.get_loc(key)
File "C:\Users\user\miniconda3\lib\site-packages\pandas\core\indexes\base.py", line 2648, in get_loc
return self._engine.get_loc(self._maybe_cast_indexer(key))
File "pandas\_libs\index.pyx", line 111, in pandas._libs.index.IndexEngine.get_loc
File "pandas\_libs\index.pyx", line 138, in pandas._libs.index.IndexEngine.get_loc
File "pandas\_libs\hashtable_class_helper.pxi", line 1619, in pandas._libs.hashtable.PyObjectHashTable.get_item
File "pandas\_libs\hashtable_class_helper.pxi", line 1627, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: 'Time'
Solved this error a month ago but completely forgot, pls help
I think there's a space in front of ' Time', you can use skipinitialspace=True:
df = pd.read_csv('test.csv', sep=',', nrows=1000, parse_dates=True, skipinitialspace=True)

Error with fit_transform in scikit learn for a movie reccommender system

This is the full code that I have tried to run.
It runs all well but there is error in the 2nd line from the bottom
count_matrix = count.fit_transform(df['bag_of_words'])
I also don't know where this bag_of_word comes from..Please suggest Code Edit..
import pandas as pd
from rake_nltk import Rake
import numpy as np
from sklearn.metrics.pairwise import cosine_similarity
from sklearn.feature_extraction.text import CountVectorizer
df = pd.read_csv('https://query.data.world/s/uikepcpffyo2nhig52xxeevdialfl7')
df = df[['Title','Genre','Director','Actors','Plot']]
df.head()
# initializing the new column
df['Key_words'] = ""
for index, row in df.iterrows():
plot = row['Plot']
r = Rake()
r.extract_keywords_from_text(plot)
key_words_dict_scores = r.get_word_degrees()
row['Key_words'] = list(key_words_dict_scores.keys())
df.drop(columns = ['Plot'], inplace = True)
count = CountVectorizer()
count_matrix = count.fit_transform(df['bag_of_words'])
cosine_sim = cosine_similarity(count_matrix, count_matrix)
The error is as follows
Traceback (most recent call last):
File "C:\Python38\lib\site-packages\pandas\core\indexes\base.py", line 2897, in get_loc
return self._engine.get_loc(key)
File "pandas/_libs/index.pyx", line 107, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/index.pyx", line 131, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/hashtable_class_helper.pxi", line 1607, in pandas._libs.hashtable.PyObjectHashTable.get_item
File "pandas/_libs/hashtable_class_helper.pxi", line 1614, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: 'bag_of_words'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "movie2.py", line 36, in <module>
count_matrix = count.fit_transform(df['bag_of_words'])
File "C:\Python38\lib\site-packages\pandas\core\frame.py", line 2995, in __getitem__
indexer = self.columns.get_loc(key)
File "C:\Python38\lib\site-packages\pandas\core\indexes\base.py", line 2899, in get_loc
return self._engine.get_loc(self._maybe_cast_indexer(key))
File "pandas/_libs/index.pyx", line 107, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/index.pyx", line 131, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/hashtable_class_helper.pxi", line 1607, in pandas._libs.hashtable.PyObjectHashTable.get_item
File "pandas/_libs/hashtable_class_helper.pxi", line 1614, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: 'bag_of_words'
Please tell me what to do?

Getting KeyError using Pandas when accessing .csv files

For some reason pandas is throwing an error when looking through some .csv stock data I have. Here is the error:
Traceback (most recent call last):
File "/usr/local/lib/python3.7/site-packages/pandas/core/indexes/base.py", line 3078, in get_loc
return self._engine.get_loc(key)
File "pandas/_libs/index.pyx", line 140, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/index.pyx", line 162, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/hashtable_class_helper.pxi", line 1492, in pandas._libs.hashtable.PyObjectHashTable.get_item
File "pandas/_libs/hashtable_class_helper.pxi", line 1500, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: 'Date'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "./python-for-finance-7.py", line 75, in
compile_data()
File "./python-for-finance-7.py", line 59, in compile_data
df.set_index('Date', inplace=True)
File "/usr/local/lib/python3.7/site-packages/pandas/core/frame.py", >line 3909, in set_index
level = frame[col]._values
File "/usr/local/lib/python3.7/site-packages/pandas/core/frame.py", >line 2688, in getitem
return self._getitem_column(key)
File "/usr/local/lib/python3.7/site-packages/pandas/core/frame.py", >line 2695, in _getitem_column
return self._get_item_cache(key)
File "/usr/local/lib/python3.7/site-packages/pandas/core/generic.py", line 2489, in _get_item_cache
values = self._data.get(item)
File "/usr/local/lib/python3.7/site->packages/pandas/core/internals.py", line 4115, in get
loc = self.items.get_loc(item)
File "/usr/local/lib/python3.7/site-packages/pandas/core/indexes/base.py", line 3080, in get_loc> return self._engine.get_loc(self._maybe_cast_indexer(key))
File "pandas/_libs/index.pyx", line 140, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/index.pyx", line 162, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/hashtable_class_helper.pxi", line 1492, in pandas._libs.hashtable.PyObjectHashTable.get_item
File "pandas/_libs/hashtable_class_helper.pxi", line 1500, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: 'Date'
to this code:
import bs4 as bs
import datetime as dt
import os
import pandas as pd
import pandas_datareader.data as web
import pickle
import requests
def compile_data():
with open("sp500tickers.pickle","rb") as f:
tickers = pickle.load(f)
main_df = pd.DataFrame()
for count,ticker in enumerate(tickers):
df = pd.read_csv('stock_dfs/{}.csv'.format(ticker),
delimiter=',', encoding="utf-8-sig")
df.set_index('Date', inplace=True)
df.rename(columns = {'Adj Close':ticker}, inplace=True)
df.drop(['High','Low','Open','Close','Volume'], 1, inplace=True)
if main_df.empty:
main_df = df
else:
main_df = main_df.join(df, how='outer')
print(count)
print(main_df.head())
main_df.to_csv('sp500_joined_closes.csv')
compile_data()
The data in the CSV files is arranged like this:
Date High Low Open Close Volume Adj. Close
yyyy-mm-dd $$ $$ $$ $$ $$ $$
I tried changing the casing of Date (ie changing Date to date) but it just moves on to throw another
KeyError:"['High', 'Low', 'Open', 'Close', 'Volume'] not found in axis
Can someone please help??
It looks like you're using the wrong delineator. The file is white-space delineated, not comma delineated.
Try using a whitespace delineator:
df = pd.read_csv('stock_dfs/{}.csv'.format(ticker),
delimiter=r'\s+', encoding="utf-8-sig")
In my case, I didn't have any entries when setting the index, the data frame was empty.
It's worth checking
if len(df) > 0:
before setting the index

Pandas reading html table

import pandas as pd
import pandas_datareader.data as web
coins = pd.read_html('https://coinmarketcap.com/')
for name in coins[0][1][1:]:
print(name)
Results in the error message below. When I print coins, I get the complete table, but when I try and get specific info it gives me this error message. I know this format works as I have copied it exactly from other exercises I have been learning from, and have just changed the website. Many thanks.
C:\Users\AppData\Local\Programs\Python\Python36-32\python.exe C:/Users/Desktop/python_work/crypto/crypto_corr.py
Traceback (most recent call last):
File "C:\Users\AppData\Local\Programs\Python\Python36-32\lib\site-packages\pandas\core\indexes\base.py", line 2525, in get_loc
return self._engine.get_loc(key)
File "pandas\_libs\index.pyx", line 117, in pandas._libs.index.IndexEngine.get_loc
File "pandas\_libs\index.pyx", line 139, in pandas._libs.index.IndexEngine.get_loc
File "pandas\_libs\hashtable_class_helper.pxi", line 1265, in pandas._libs.hashtable.PyObjectHashTable.get_item
File "pandas\_libs\hashtable_class_helper.pxi", line 1273, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: 1
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:/Users/Desktop/python_work/crypto/crypto_corr.py", line 6, in <module>
for name in coins[0][1][1:]:
File "C:\Users\AppData\Local\Programs\Python\Python36-32\lib\site-packages\pandas\core\frame.py", line 2139, in __getitem__
return self._getitem_column(key)
File "C:\Users\AppData\Local\Programs\Python\Python36-32\lib\site-packages\pandas\core\frame.py", line 2146, in _getitem_column
return self._get_item_cache(key)
File "C:\Users\AppData\Local\Programs\Python\Python36-32\lib\site-packages\pandas\core\generic.py", line 1842, in _get_item_cache
values = self._data.get(item)
File "C:\Users\AppData\Local\Programs\Python\Python36-32\lib\site-packages\pandas\core\internals.py", line 3843, in get
loc = self.items.get_loc(item)
File "C:\Users\AppData\Local\Programs\Python\Python36-32\lib\site-packages\pandas\core\indexes\base.py", line 2527, in get_loc
return self._engine.get_loc(self._maybe_cast_indexer(key))
File "pandas\_libs\index.pyx", line 117, in pandas._libs.index.IndexEngine.get_loc
File "pandas\_libs\index.pyx", line 139, in pandas._libs.index.IndexEngine.get_loc
File "pandas\_libs\hashtable_class_helper.pxi", line 1265, in pandas._libs.hashtable.PyObjectHashTable.get_item
File "pandas\_libs\hashtable_class_helper.pxi", line 1273, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: 1
Process finished with exit code 1
If df is a dataframe, indexing like df[column] looks for columns called column. In your case, coins[0] is a dataframe, which does not have a column 1. However, it does have a column Name, so to print all names do the following:
df = coins[0]
for name in df['Name']:
print(name)

Categories