I would like to compare log and pct change f the two symbols, but the following error appears:
KeyError: 'Adj Close'
import datetime
import pandas as pd
import numpy as np
import yfinance as yf
start = datetime.datetime(2017, 10, 1)
end = datetime.datetime.now()
symbols = ['BTC-USD', 'ETH-USD']
df = pd.DataFrame()
for i in symbols:
data = yf.download(i, start=None, end=None,show_errors=("True"),
period="4y", interval="1mo")
df[i] = data['Adj Close'].pct_change().dropna()
df['log_stuff'] = \
np.log(df['Adj Close'].astype('float64')/df['Adj Close'].astype('float64').shift(1))
df[['pct_change', 'log_stuff','df']].plot();
You could try the following. Please note, that you can also pass a list to download(), so no loops are required.
import numpy as np
import pandas as pd
import yfinance as yf
symbols = ['BTC-USD', 'ETH-USD']
data = yf.download(symbols, period="4y", interval="1mo")
# calculate pct return
pct_data = data['Adj Close'].pct_change()
pct_data = pct_data.add_suffix('_pct')
# calculate log returns
log_data = np.log(data['Adj Close']) - np.log(data['Adj Close'].shift(1))
log_data = log_data.add_suffix('_log')
# combine returns and drop na values
combined_data = pd.concat([pct_data,log_data], axis=1).dropna()
print(combined_data)
This will yield the following output:
BTC-USD_pct ETH-USD_pct BTC-USD_log ETH-USD_log
Date
2017-12-01 0.383326 0.692483 0.324490 0.526197
2018-01-01 -0.277987 0.477813 -0.325713 0.390564
2018-02-01 0.017298 -0.235276 0.017150 -0.268240
...
Related
I am trying loop the ChiSquare test and outcome is not shown as required, that is in Dataframe.
All columns are coming one row..
Please help
# Import the function
from scipy.stats import chi2_contingency
chi2_check = []
for i in df_clean.select_dtypes(['object']):
if chi2_contingency(pd.crosstab(df_clean['Final_Comments'], df_clean[i]))[1] < 0.05:
chi2_check.append('Reject Null Hypothesis')
else:
chi2_check.append('Fail to Reject Null Hypothesis')
res = pd.DataFrame(data = [df_clean.select_dtypes(['object']), chi2_check]
).T
res.columns = ['Column', 'Hypothesis']
print(res)
res.columns
import os
import sys
import json
import requests
import isodate
import pandas as pd
from pandas import ExcelWriter
from pandas import ExcelFile
pd.set_option('display.max_rows', None)
pd.set_option('display.max_columns', None)
pd.set_option('display.width', None)
bufsize=1024
session = requests.Session()
session.trust_env=False
path = os.getcwd()
print(path)
format(os.getcwd())
os.chdir('/raj')
file_name = pd.read_excel('repos_desc12_p61qr.xlsx')
file2 = open("commit_details.csv", "w+", buffering=bufsize)
file3 = open("merge_details.csv", "w+", buffering=bufsize)
hostname = "https://bsp-os.git.visteon.com"
private = "-rBpd_x15GRTmFkk_T9H"
def excel_parser(meExcel):
dict_format = meExcel.to_dict(orient='record')
#print(dict_format.columns.ravel())
#dict_format = json.loads(dict_format)
#print(dict_format)
for repo_detail in dict_format:
parsed_repo_path = repo_detail["REPO"]
#print(parsed_repo_path)
parsed_branch_name = repo_detail["BranchName"]
#print(parsed_branch_name)
parsed_duration = repo_detail["StartDate"]
while am trying to run and take input through pipeline , the " EOFError: EOF when reading a line " is occuring i tried error exception but not working please help to get the input from python file through jenkins pipeline
my code is
import streamlit as st
import pickle
import string
from nltk.corpus import stopwords
import nltk
from nltk.stem.porter import PorterStemmer
ps = PorterStemmer()
def transform_text(text):
text = text.lower()
text = nltk.word_tokenize(text)
y = []
for i in text:
if i.isalnum():
y.append(i)
text = y[:]
y.clear()
for i in text:
if i not in stopwords.words('english') and i not in string.punctuation:
y.append(i)
text = y[:]
y.clear()
for i in text:
y.append(ps.stem(i))
return " ".join(y)
tfidf = pickle.load(open('vectorizer.pkl','rb'))
model = pickle.load(open('model.pkl','rb'))
st.title("Email/SMS Spam Classifier")
input_sms = st.text_area("Enter the message")
if st.button('Predict'):
# 1. preprocess
transformed_sms = transform_text(input_sms)
# 2. vectorize
vector_input = tfidf.transform([transformed_sms])
# 3. predict
result = model.predict(vector_input)[0]
# 4. Display
if result == 1:
st.header("Spam")
else:
st.header("Not Spam")
Code for a single raster file:
import geopandas as gpd
#import os
import rasterio
import scipy.sparse as sparse
import pandas as pd
import numpy as np
# Create an empty pandas dataframe called 'table'
table = pd.DataFrame(index = np.arange(0,1))
# Read the points shapefile using GeoPandas
stations = gpd.read_file(r'E:/anakonda/Shape files/AAQ_st1/AAQ_ST1.shp')
stations['lon'] = stations['geometry'].x
stations['lat'] = stations['geometry'].y
Matrix = pd.DataFrame()
# Iterate through the rasters and save the data as individual arrays to a Matrix
dataset = rasterio.open(r'E:/anakonda/LST_day/MOD11A1.006_LST_Day_1km_doy2019082_aid0001.tif')
data_array = dataset.read(1)
data_array_sparse = sparse.coo_matrix(data_array, shape = (351, 545))
for records_date in Matrix.columns.tolist():
a = Matrix
LST_day_value = a.loc[int(row)][int(col)]
table[records_date] = LST_day_value
transpose_mat = table.T
transpose_mat.rename(columns = {0: 'LST_Day(Kel)'}, inplace = True)
transpose_mat.to_csv(r'E:/anakonda/LST_day'+'\\'+station_name+'.csv')
Error code lines:
LST_day_value = a.loc[int(row)][int(col)]
transpose_mat.to_csv(r'E:/anakonda/LST_day'+'\'+station_name+'.csv')
Errors Shown:
Undefined Name 'row' (pyflakes E)
Undefined Name 'col' (pyflakes E)
NameError: name 'transpose_mat' is not defined
I'm using the above code for creating a Raster Time-series for Modis LST data. the code ran well till 'transposing the matrix'. the error shown is mentioned below the code. Im new to python, so kindly help me with this issue.
import os
import rasterio
import scipy.sparse as sparse
import pandas as pd
import numpy as np
# Create an empty pandas dataframe called 'table'
table = pd.DataFrame(index = np.arange(0,1))
# Read the points shapefile using GeoPandas
stations = gpd.read_file(r'E:/anakonda/Shape files/AAQ_st1/AAQ_ST1.shp')
stations['lon'] = stations['geometry'].x
stations['lat'] = stations['geometry'].y
Matrix = pd.DataFrame()
# Iterate through the rasters and save the data as individual arrays to a Matrix
for files in os.listdir(r'E:/anakonda/LST_Night'):
if files[-4: ] == '.tif':
dataset = rasterio.open(r'E:/anakonda/LST_Night'+'\\'+files)
data_array = dataset.read(1)
data_array_sparse = sparse.coo_matrix(data_array, shape = (351,545))
data = files[ :-20]
Matrix[data] = data_array_sparse.toarray().tolist()
print('Processing is done for the raster: '+ files[:-20])
# Iterate through the stations and get the corresponding row and column for the related x, y coordinates
for index, row in stations.iterrows():
station_name = str(row['Station'])
lon = float(row['lon'])
lat = float(row['lat'])
x,y = (lon, lat)
row, col = dataset.index(x, y)
print('Processing: '+ station_name)
# Pick the LST value from each stored raster array and record it into the previously created 'table'
for records_date in Matrix.columns.tolist():
a = Matrix[records_date]
LST_Night_value = a.loc[int(row)][int(col)]
table[records_date] = LST_Night_value
transpose_mat = table.T
transpose_mat.rename(columns = {0: 'LstNight(Kel)'}, inplace = True)
transpose_mat.to_csv(r'E:/anakonda/LST_Night'+'\\'+station_name+'.csv')```
This is the error shown:
```File "C:\Anaconda\envs\timeseries\lib\site-packages\pandas\core\indexes\range.py", line 357, in get_loc
raise KeyError(key) from err
KeyError: 2278```
Given a simple feature selection code below, I want to know the selected columns after the feature selection (The dataset includes a header V1 ... V20)
import pandas as pd
from sklearn.feature_selection import SelectFromModel, SelectKBest, f_regression
def feature_selection(data):
y = data['Class']
X = data.drop(['Class'], axis=1)
fs = SelectKBest(score_func=f_regression, k=10)
# Applying feature selection
X_selected = fs.fit_transform(X, y)
# TODO: determine the columns being selected
return X_selected
data = pd.read_csv("../dataset.csv")
new_data = feature_selection(data)
I appreciate any help.
I have used the iris dataset for my example but you can probably easily modify your code to match your use case.
The SelectKBest method has the scores_ attribute I used to sort the features.
Feel free to ask for any clarifications.
import pandas as pd
import numpy as np
from sklearn.feature_selection import SelectFromModel, SelectKBest, f_regression
from sklearn.datasets import load_iris
def feature_selection(data):
y = data[1]
X = data[0]
column_names = ["A", "B", "C", "D"] # Here you should use your dataframe's column names
k = 2
fs = SelectKBest(score_func=f_regression, k=k)
# Applying feature selection
X_selected = fs.fit_transform(X, y)
# Find top features
# I create a list like [[ColumnName1, Score1] , [ColumnName2, Score2], ...]
# Then I sort in descending order on the score
top_features = sorted(zip(column_names, fs.scores_), key=lambda x: x[1], reverse=True)
print(top_features[:k])
return X_selected
data = load_iris(return_X_y=True)
new_data = feature_selection(data)
I don't know the in-build method, but it can be easily coded.
n_columns_selected = X_new.shape[0]
new_columns = list(sorted(zip(fs.scores_, X.columns))[-n_columns_selected:])
# new_columns order is perturbed, we need to restore it. We use the names of the columns of X as a reference
new_columns = list(sorted(cols_new, key=lambda x: list(X.columns).index(x)))