
import requests


url = 'https://www.alphavantage.co/query'
API_KEY  = "UKVFE0JLE0TBPDEF"

params = {"function":"TIME_SERIES_INTRADAY",
          "apikey":API_KEY,
          "symbol":"IBM",
          "interval":"15min",
         }

r = requests.get(url, params)

r

<Response [200]>


import pandas as pd
pd.DataFrame(r.json()['Time Series (15min)']).transpose()


def get_data(ticker):
    url = 'https://www.alphavantage.co/query'
    API_KEY  = "UKVFE0JLE0TBPDEF"

    params = {"function":"TIME_SERIES_INTRADAY",
          "apikey":API_KEY,
          "symbol":ticker,
          "interval":"15min",
         }

    r = requests.get(url, params)
    df = pd.DataFrame(r.json()['Time Series (15min)']).transpose()
    df['symbol'] = ticker # will add a new column symbol
    return df

def combined_daily_time_series(tickers):
    dataframes = [get_data(t) for t in tickers]
    return pd.concat(dataframes)


combined_daily_time_series(["IBM"])


combined_daily_time_series(["IBM","AAPL"])


def get_data(ticker):
    url = 'https://www.alphavantage.co/query'
    API_KEY  = "UKVFE0JLE0TBPDEF"

    params = {"function":"TIME_SERIES_INTRADAY",
          "apikey":API_KEY,
          "symbol":ticker,
          "interval":"15min",
         }

    r = requests.get(url, params)
    df = pd.DataFrame(r.json()['Time Series (15min)']).transpose()
    df['symbol'] = ticker # will add a new column symbol
    oldnames = ['1. open', '2. high', '3. low', '4. close', '5. volume']
    newnames = ["open", "high", "low", "close", "volume"]
    df = df.rename(columns=dict(zip(oldnames,newnames)))
    for c in newnames:
        df[c] = pd.to_numeric(df[c])
    return df

def combined_daily_time_series(tickers):
    dataframes = [get_data(t) for t in tickers]
    return pd.concat(dataframes)


df = combined_daily_time_series(["IBM","AAPL"])

df


df.info()

<class 'pandas.core.frame.DataFrame'>
Index: 200 entries, 2023-03-29 18:30:00 to 2023-03-28 11:15:00
Data columns (total 6 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   open    200 non-null    float64
 1   high    200 non-null    float64
 2   low     200 non-null    float64
 3   close   200 non-null    float64
 4   volume  200 non-null    int64  
 5   symbol  200 non-null    object 
dtypes: float64(4), int64(1), object(1)
memory usage: 10.9+ KB

import pandas as pd
import requests

def combined_daily_time_series(symbols):
    dfs = []
    for symbol in symbols:
        url = f"https://www.alphavantage.co/query?function=TIME_SERIES_DAILY_ADJUSTED&symbol={symbol}&outputsize=full&apikey=<FG5B837V8HPIRTOO>"
        response = requests.get(url)
        data = response.json()["Time Series (Daily)"]
        df = pd.DataFrame.from_dict(data, orient="index")
        df = df.rename(columns={
            "1. open": "open",
            "2. high": "high",
            "3. low": "low",
            "4. close": "close",
            "6. volume": "volume"
        })
        df["symbol"] = symbol
        dfs.append(df)
    combined_df = pd.concat(dfs)
    combined_df = combined_df.apply(pd.to_numeric) # this will apply even to 'symbol'
    return combined_df

def get_total_volume(df):
    return df.groupby("symbol")["volume"].sum()

df


import pandas as pd
import requests

def combined_daily_time_series(symbols):
    dfs = []
    for symbol in symbols:
        url = f"https://www.alphavantage.co/query?function=TIME_SERIES_DAILY_ADJUSTED&symbol={symbol}&outputsize=full&apikey=<FG5B837V8HPIRTOO>"
        response = requests.get(url)
        data = response.json()["Time Series (Daily)"]
        df = pd.DataFrame.from_dict(data, orient="index")
        df = df.rename(columns={
            "1. open": "open",
            "2. high": "high",
            "3. low": "low",
            "4. close": "close",
            "6. volume": "volume"
        })
        df["symbol"] = symbol
        dfs.append(df)
    combined_df = pd.concat(dfs)
    combined_df = combined_df.apply(pd.to_numeric)
    return combined_df

def get_total_volume(df):
    return df.groupby("symbol")["volume"].sum()


get_total_volume(df)

symbol
AAPL    72659191
IBM      8614473
Name: volume, dtype: int64


def get_max_volume(df):
    return df.groupby("symbol")["volume"].max()


get_max_volume(df)

symbol
AAPL    4985474
IBM      952777
Name: volume, dtype: int64


def latest_jobs(location):
    url = "https://careers.arcesium.com/go/All-Jobs/4687610/"
    return pd.read_html(url)


latest_jobs("sdometjhr")

[                                                Title  \
 0   Senior Software Engineer - Data Platform  Seni...   
 1   Principal Engineer  Principal Engineer  Hydera...   
 2   Senior Principal Engineer  Senior Principal En...   
 3   Principal Engineer - Front End  Principal Engi...   
 4   Sales Executive - Institutional Asset Managers...   
 5   Product Lead - Compliance  Product Lead - Comp...   
 6   Designer-Returnship  Designer-Returnship  Hyde...   
 7   Technical Lead  Technical Lead  Hyderabad, TG,...   
 8   Business Strategy Lead  Business Strategy Lead...   
 9   Associate Consultant - PCG - PNS  Associate Co...   
 10  Senior Analyst, Sales Ops  Senior Analyst, Sal...   
 11  Senior Specialist, Admin  Senior Specialist, A...   
 12  Associate Director - Test Engineering  Associa...   
 13  Principal Engineer - Linux and Infrastructure ...   
 14  Distributed Systems Engineer (Remote Eligible)...   
 15  Senior Specialist-MCA  Senior Specialist-MCA  ...   
 16  Manager, Sales Enablement  Manager, Sales Enab...   
 17  Sr Manager, Learning and Development  Sr Manag...   
 18  Manager, Organization Development  Manager, Or...   
 19  Software Engineer - Forward Deployed Team (Rem...   
 20  Technical Writer-Returnship  Technical Writer-...   
 21  Manager, PMO  Manager, PMO  Gurugram, HR, IN  ...   
 22  Specialist, HR Business Partner  Specialist, H...   
 23  Principal Engineer - Machine Learning  Princip...   
 24  Solutions Architect - Treasury (Functional), S...   
 
                        Location  
 0              New York, NY, US  
 1   Hyderabad, TG, IN  +2 more…  
 2   Hyderabad, TG, IN  +2 more…  
 3   Hyderabad, TG, IN  +2 more…  
 4              New York, NY, US  
 5             Hyderabad, TG, IN  
 6   Hyderabad, TG, IN  +2 more…  
 7   Hyderabad, TG, IN  +2 more…  
 8              New York, NY, US  
 9             Hyderabad, TG, IN  
 10            Hyderabad, TG, IN  
 11            Bengaluru, KA, IN  
 12  Bengaluru, KA, IN  +1 more…  
 13   Gurugram, HR, IN  +2 more…  
 14             New York, NY, US  
 15            Bengaluru, KA, IN  
 16            Hyderabad, TG, IN  
 17            Hyderabad, TG, IN  
 18            Hyderabad, TG, IN  
 19             New York, NY, US  
 20  Hyderabad, TG, IN  +2 more…  
 21             Gurugram, HR, IN  
 22             Gurugram, HR, IN  
 23            Hyderabad, TG, IN  
 24  Hyderabad, TG, IN  +2 more…  ]


def latest_jobs(location):
    url = "https://careers.arcesium.com/go/All-Jobs/4687610/"
    return pd.read_html(url)[0]


df = latest_jobs("ddsf")


df.columns

Index(['Title', 'Location'], dtype='object')


df[df.Location == "Hyderabad, TG, IN"]


df[df.Location.str.contains("Hyderabad")]


def latest_jobs(location):
    url = "https://careers.arcesium.com/go/All-Jobs/4687610/"
    df = pd.read_html(url)[0]
    return df[df.Location.str.contains(location)]


latest_jobs("Hyderabad")

import pandas as pd
import requests

def latest_jobs(location):
    url = 'https://careers.arcesium.com/go/All-Jobs/4687610/'
    response = requests.get(url)
    response.raise_for_status()
    data = response.text
    df = pd.read_html(data, attrs={'class': 'JobListingsTable'})[0]
    df = df[['Job Title', 'Location']]
    df = df[df['Location'].str.contains(location)]
    df.reset_index(drop=True, inplace=True)
    return df.head(25)


import pandas as pd
import requests

def latest_jobs(location):
    url = 'https://careers.arcesium.com/go/All-Jobs/4687610/'
    response = requests.get(url)
    response.raise_for_status()
    data = response.text
    df = pd.read_html(data, attrs={'class': 'JobListingsTable'})[0]
    df = df[['Job Title', 'Location']]
    df = df[df['Location'].str.contains(location)]
    df.reset_index(drop=True, inplace=True)
    return df.head(25)


latest_jobs("Hyderabad")

---------------------------------------------------------------------------
ImportError                               Traceback (most recent call last)
Cell In[68], line 1
----> 1 latest_jobs("Hyderabad")

Cell In[67], line 9, in latest_jobs(location)
      7 response.raise_for_status()
      8 data = response.text
----> 9 df = pd.read_html(data, attrs={'class': 'JobListingsTable'})[0]
     10 df = df[['Job Title', 'Location']]
     11 df = df[df['Location'].str.contains(location)]

File ~/usr/local/default/lib/python3.10/site-packages/pandas/util/_decorators.py:331, in deprecate_nonkeyword_arguments.<locals>.decorate.<locals>.wrapper(*args, **kwargs)
    325 if len(args) > num_allow_args:
    326     warnings.warn(
    327         msg.format(arguments=_format_argument_list(allow_args)),
    328         FutureWarning,
    329         stacklevel=find_stack_level(),
    330     )
--> 331 return func(*args, **kwargs)

File ~/usr/local/default/lib/python3.10/site-packages/pandas/io/html.py:1205, in read_html(io, match, flavor, header, index_col, skiprows, attrs, parse_dates, thousands, encoding, decimal, converters, na_values, keep_default_na, displayed_only, extract_links)
   1201 validate_header_arg(header)
   1203 io = stringify_path(io)
-> 1205 return _parse(
   1206     flavor=flavor,
   1207     io=io,
   1208     match=match,
   1209     header=header,
   1210     index_col=index_col,
   1211     skiprows=skiprows,
   1212     parse_dates=parse_dates,
   1213     thousands=thousands,
   1214     attrs=attrs,
   1215     encoding=encoding,
   1216     decimal=decimal,
   1217     converters=converters,
   1218     na_values=na_values,
   1219     keep_default_na=keep_default_na,
   1220     displayed_only=displayed_only,
   1221     extract_links=extract_links,
   1222 )

File ~/usr/local/default/lib/python3.10/site-packages/pandas/io/html.py:982, in _parse(flavor, io, match, attrs, encoding, displayed_only, extract_links, **kwargs)
    980 retained = None
    981 for flav in flavor:
--> 982     parser = _parser_dispatch(flav)
    983     p = parser(io, compiled_match, attrs, encoding, displayed_only, extract_links)
    985     try:

File ~/usr/local/default/lib/python3.10/site-packages/pandas/io/html.py:931, in _parser_dispatch(flavor)
    929 if flavor in ("bs4", "html5lib"):
    930     if not _HAS_HTML5LIB:
--> 931         raise ImportError("html5lib not found, please install it")
    932     if not _HAS_BS4:
    933         raise ImportError("BeautifulSoup4 (bs4) not found, please install it")

ImportError: html5lib not found, please install it


!pip install html5lib

Collecting html5lib
  Using cached html5lib-1.1-py2.py3-none-any.whl (112 kB)
Requirement already satisfied: webencodings in /home/vikrant/usr/local/default/lib/python3.10/site-packages (from html5lib) (0.5.1)
Requirement already satisfied: six>=1.9 in /home/vikrant/usr/local/default/lib/python3.10/site-packages (from html5lib) (1.16.0)
Installing collected packages: html5lib
Successfully installed html5lib-1.1


import pandas as pd
import requests

def latest_jobs(location):
    url = 'https://careers.arcesium.com/go/All-Jobs/4687610/'
    response = requests.get(url)
    response.raise_for_status()
    data = response.text
    df = pd.read_html(data, attrs={'class': 'JobListingsTable'})[0]
    df = df[['Job Title', 'Location']]
    df = df[df['Location'].str.contains(location)]
    df.reset_index(drop=True, inplace=True)
    return df.head(25)

latest_jobs("Hyderabad")

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Cell In[1], line 15
     12     df.reset_index(drop=True, inplace=True)
     13     return df.head(25)
---> 15 latest_jobs("Hyderabad")

Cell In[1], line 9, in latest_jobs(location)
      7 response.raise_for_status()
      8 data = response.text
----> 9 df = pd.read_html(data, attrs={'class': 'JobListingsTable'})[0]
     10 df = df[['Job Title', 'Location']]
     11 df = df[df['Location'].str.contains(location)]

File ~/usr/local/default/lib/python3.10/site-packages/pandas/util/_decorators.py:331, in deprecate_nonkeyword_arguments.<locals>.decorate.<locals>.wrapper(*args, **kwargs)
    325 if len(args) > num_allow_args:
    326     warnings.warn(
    327         msg.format(arguments=_format_argument_list(allow_args)),
    328         FutureWarning,
    329         stacklevel=find_stack_level(),
    330     )
--> 331 return func(*args, **kwargs)

File ~/usr/local/default/lib/python3.10/site-packages/pandas/io/html.py:1205, in read_html(io, match, flavor, header, index_col, skiprows, attrs, parse_dates, thousands, encoding, decimal, converters, na_values, keep_default_na, displayed_only, extract_links)
   1201 validate_header_arg(header)
   1203 io = stringify_path(io)
-> 1205 return _parse(
   1206     flavor=flavor,
   1207     io=io,
   1208     match=match,
   1209     header=header,
   1210     index_col=index_col,
   1211     skiprows=skiprows,
   1212     parse_dates=parse_dates,
   1213     thousands=thousands,
   1214     attrs=attrs,
   1215     encoding=encoding,
   1216     decimal=decimal,
   1217     converters=converters,
   1218     na_values=na_values,
   1219     keep_default_na=keep_default_na,
   1220     displayed_only=displayed_only,
   1221     extract_links=extract_links,
   1222 )

File ~/usr/local/default/lib/python3.10/site-packages/pandas/io/html.py:1006, in _parse(flavor, io, match, attrs, encoding, displayed_only, extract_links, **kwargs)
   1004 else:
   1005     assert retained is not None  # for mypy
-> 1006     raise retained
   1008 ret = []
   1009 for table in tables:

File ~/usr/local/default/lib/python3.10/site-packages/pandas/io/html.py:986, in _parse(flavor, io, match, attrs, encoding, displayed_only, extract_links, **kwargs)
    983 p = parser(io, compiled_match, attrs, encoding, displayed_only, extract_links)
    985 try:
--> 986     tables = p.parse_tables()
    987 except ValueError as caught:
    988     # if `io` is an io-like object, check if it's seekable
    989     # and try to rewind it before trying the next parser
    990     if hasattr(io, "seekable") and io.seekable():

File ~/usr/local/default/lib/python3.10/site-packages/pandas/io/html.py:262, in _HtmlFrameParser.parse_tables(self)
    254 def parse_tables(self):
    255     """
    256     Parse and return all tables from the DOM.
    257 
   (...)
    260     list of parsed (header, body, footer) tuples from tables.
    261     """
--> 262     tables = self._parse_tables(self._build_doc(), self.match, self.attrs)
    263     return (self._parse_thead_tbody_tfoot(table) for table in tables)

File ~/usr/local/default/lib/python3.10/site-packages/pandas/io/html.py:618, in _BeautifulSoupHtml5LibFrameParser._parse_tables(self, doc, match, attrs)
    615 tables = doc.find_all(element_name, attrs=attrs)
    617 if not tables:
--> 618     raise ValueError("No tables found")
    620 result = []
    621 unique_tables = set()

ValueError: No tables found


import pandas as pd
import requests

def latest_jobs(location):
    url = 'https://careers.arcesium.com/go/All-Jobs/4687610/'
    response = requests.get(url)
    response.raise_for_status()
    data = response.text
    df = pd.read_html(data)[0]
    df = df[df['Location'].str.contains(location)]
    df.reset_index(drop=True, inplace=True)
    return df.head(25)

latest_jobs("Hyderabad")

	1. open	2. high	3. low	4. close	5. volume
2023-03-29 18:30:00	129.5800	129.5800	129.5800	129.5800	100
2023-03-29 18:15:00	129.7200	129.7200	129.5800	129.5800	200
2023-03-29 17:45:00	129.7200	129.7200	129.7200	129.7200	100
2023-03-29 17:30:00	129.6500	129.6500	129.6500	129.6500	200
2023-03-29 17:15:00	129.6000	129.6000	129.6000	129.6000	301
...	...	...	...	...	...
2023-03-27 13:15:00	129.3200	129.4350	129.1600	129.2400	103222
2023-03-27 13:00:00	129.2900	129.3250	129.1938	129.3100	85797
2023-03-27 12:45:00	129.2600	129.3100	129.1700	129.2500	79987
2023-03-27 12:30:00	129.0100	129.2800	128.9690	129.2500	123038
2023-03-27 12:15:00	128.9600	129.0900	128.9100	129.0141	117268

	1. open	2. high	3. low	4. close	5. volume	symbol
2023-03-29 18:30:00	129.5800	129.5800	129.5800	129.5800	100	IBM
2023-03-29 18:15:00	129.7200	129.7200	129.5800	129.5800	200	IBM
2023-03-29 17:45:00	129.7200	129.7200	129.7200	129.7200	100	IBM
2023-03-29 17:30:00	129.6500	129.6500	129.6500	129.6500	200	IBM
2023-03-29 17:15:00	129.6000	129.6000	129.6000	129.6000	301	IBM
...	...	...	...	...	...	...
2023-03-27 13:15:00	129.3200	129.4350	129.1600	129.2400	103222	IBM
2023-03-27 13:00:00	129.2900	129.3250	129.1938	129.3100	85797	IBM
2023-03-27 12:45:00	129.2600	129.3100	129.1700	129.2500	79987	IBM
2023-03-27 12:30:00	129.0100	129.2800	128.9690	129.2500	123038	IBM
2023-03-27 12:15:00	128.9600	129.0900	128.9100	129.0141	117268	IBM

	1. open	2. high	3. low	4. close	5. volume	symbol
2023-03-29 18:30:00	129.5800	129.5800	129.5800	129.5800	100	IBM
2023-03-29 18:15:00	129.7200	129.7200	129.5800	129.5800	200	IBM
2023-03-29 17:45:00	129.7200	129.7200	129.7200	129.7200	100	IBM
2023-03-29 17:30:00	129.6500	129.6500	129.6500	129.6500	200	IBM
2023-03-29 17:15:00	129.6000	129.6000	129.6000	129.6000	301	IBM
...	...	...	...	...	...	...
2023-03-28 12:15:00	156.9200	156.9500	156.5400	156.6800	892032	AAPL
2023-03-28 12:00:00	156.9300	157.0300	156.7502	156.9100	1203419	AAPL
2023-03-28 11:45:00	156.6000	157.0000	156.5750	156.9200	1466377	AAPL
2023-03-28 11:30:00	156.7750	156.8900	156.3900	156.6000	1258754	AAPL
2023-03-28 11:15:00	156.4400	156.9000	156.4050	156.7776	1387565	AAPL

	open	high	low	close	volume	symbol
2023-03-29 18:30:00	129.580	129.58	129.5800	129.5800	100	IBM
2023-03-29 18:15:00	129.720	129.72	129.5800	129.5800	200	IBM
2023-03-29 17:45:00	129.720	129.72	129.7200	129.7200	100	IBM
2023-03-29 17:30:00	129.650	129.65	129.6500	129.6500	200	IBM
2023-03-29 17:15:00	129.600	129.60	129.6000	129.6000	301	IBM
...	...	...	...	...	...	...
2023-03-28 12:15:00	156.920	156.95	156.5400	156.6800	892032	AAPL
2023-03-28 12:00:00	156.930	157.03	156.7502	156.9100	1203419	AAPL
2023-03-28 11:45:00	156.600	157.00	156.5750	156.9200	1466377	AAPL
2023-03-28 11:30:00	156.775	156.89	156.3900	156.6000	1258754	AAPL
2023-03-28 11:15:00	156.440	156.90	156.4050	156.7776	1387565	AAPL

	open	high	low	close	volume	symbol
2023-03-29 18:30:00	129.580	129.58	129.5800	129.5800	100	IBM
2023-03-29 18:15:00	129.720	129.72	129.5800	129.5800	200	IBM
2023-03-29 17:45:00	129.720	129.72	129.7200	129.7200	100	IBM
2023-03-29 17:30:00	129.650	129.65	129.6500	129.6500	200	IBM
2023-03-29 17:15:00	129.600	129.60	129.6000	129.6000	301	IBM
...	...	...	...	...	...	...
2023-03-28 12:15:00	156.920	156.95	156.5400	156.6800	892032	AAPL
2023-03-28 12:00:00	156.930	157.03	156.7502	156.9100	1203419	AAPL
2023-03-28 11:45:00	156.600	157.00	156.5750	156.9200	1466377	AAPL
2023-03-28 11:30:00	156.775	156.89	156.3900	156.6000	1258754	AAPL
2023-03-28 11:15:00	156.440	156.90	156.4050	156.7776	1387565	AAPL

Python Virtual Training For Arcesium - Module III - Nurturing Session¶

Problem 1¶

How do we combine dataframe?¶

Aakash¶

Problem 2¶

Aakash's solution¶

	Title	Location
5	Product Lead - Compliance Product Lead - Comp...	Hyderabad, TG, IN
9	Associate Consultant - PCG - PNS Associate Co...	Hyderabad, TG, IN
10	Senior Analyst, Sales Ops Senior Analyst, Sal...	Hyderabad, TG, IN
16	Manager, Sales Enablement Manager, Sales Enab...	Hyderabad, TG, IN
17	Sr Manager, Learning and Development Sr Manag...	Hyderabad, TG, IN
18	Manager, Organization Development Manager, Or...	Hyderabad, TG, IN
23	Principal Engineer - Machine Learning Princip...	Hyderabad, TG, IN

	Title	Location
1	Principal Engineer Principal Engineer Hydera...	Hyderabad, TG, IN +2 more…
2	Senior Principal Engineer Senior Principal En...	Hyderabad, TG, IN +2 more…
3	Principal Engineer - Front End Principal Engi...	Hyderabad, TG, IN +2 more…
5	Product Lead - Compliance Product Lead - Comp...	Hyderabad, TG, IN
6	Designer-Returnship Designer-Returnship Hyde...	Hyderabad, TG, IN +2 more…
7	Technical Lead Technical Lead Hyderabad, TG,...	Hyderabad, TG, IN +2 more…
9	Associate Consultant - PCG - PNS Associate Co...	Hyderabad, TG, IN
10	Senior Analyst, Sales Ops Senior Analyst, Sal...	Hyderabad, TG, IN
16	Manager, Sales Enablement Manager, Sales Enab...	Hyderabad, TG, IN
17	Sr Manager, Learning and Development Sr Manag...	Hyderabad, TG, IN
18	Manager, Organization Development Manager, Or...	Hyderabad, TG, IN
20	Technical Writer-Returnship Technical Writer-...	Hyderabad, TG, IN +2 more…
23	Principal Engineer - Machine Learning Princip...	Hyderabad, TG, IN
24	Solutions Architect - Treasury (Functional), S...	Hyderabad, TG, IN +2 more…