Please enable JavaScript.

Coggle requires JavaScript to display documents.

PYTHON - Coggle Diagram

- - - - Mixed datatypes
        
        np.genfromtxt('titanic.csv', delimiter=',', names=True, dtype=None)
        
        Type: np Structured Array
        
        np.recfromcsv(file) - defaults: delimiter= ',' & dtype=None
        
        Headers: data.dtype.names
      - Single Data type
        
        Type: np.array
        
        np.loadtxt(filename, delimiter=',')
    - - pd.read_csv(file,nrows=5, header=None)
        pd.read_csv("file.csv", index_col=0, na_values='n/a', parse_dates=['Last Upadate'])
        
        Type: pd.DataFrame
        
        Headers: data.head()
        
        Convert 2 np.array: np_array= data.values
  - - - data.sheet_names
      - df1= data.parse(sheetname, usecols=, skiprows=, names=__)
      - df1 = data.parse(sheet_index, usecols=, skiprows=, names=__)
    - - Returns: dict
  - - - from sqlalchemy import create_engine
        engine = create_engine('sqlite:///Northwind.sqlite')
        table_names = engine.table_names()
        con= engine.connect()
        rs=con.execute("SELECT * from Orders")
        df=pd.DataFrame(rs.fetchall())
        df.columns = rs.keys()
        con.close()
    - - with engine.connect() as con:
        __rs = con.execute("SELECT OrderID, OrderDate, ShipName FROM Orders")
        __df = pd.DataFrame(rs.fetchmany(size=5))
        __df.columns = rs.keys()
    - - df = pd.read_sql_query("SELECT * FROM Orders", engine)
  - - - from urllib.request import urlretrieve
        url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-white.csv'
        urlretrieve(url, 'winequality-white.csv') -> GET request
      - from urllib.request import urlopen,Request
        url = "https://campus.datacamp.com/courses/1606/4135?ex=2"
        request = Request(url)
        response = urlopen(request) -> class
        html= response.read() -> HTML text
        response.close()
    - - import requests
        url = 'https://www.wikipedia.org'
        r = requests.get(url)
        text = t.text
      - (no necesita close)
      - from bs4 import BeautifulSoup
        soup = BeautifulSoup(html_doc)
        pretty_soup = soup.prettify()
        title = soup.title
        text = soup.get_text()
      - for link in a_tags:
        __print(link.get('href'))
    - - df=pd.read_csv(url,sep=';')
  - - - import json
        with open("a_movie.json") as json_file:
        _json_data=json.load(json_file)
    - - REST API
      - TWITTER
        
        AUTHENTICATION
        
        import tweepy, json
        access_token = "..."
        access_token_secret = "..."
        consumer_key = "..."
        consumer_secret = "..."auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
        auth.set_access_token(access_token, access_token_secret)
        
        STREAM TWEETS
        
        st_class.py
        classMyStreamListener(tweepy.StreamListener):
        definit(self, api=None):
        __super(MyStreamListener, self).init()
        __self.num_tweets = 0
        self.file = open("tweets.txt", "w")defon_status(self, status): tweet = status._json self.file.write(json.dumps(tweet) + '\n') tweet_list.append(status) self.num_tweets += 1
        if self.num_tweets < 100:
        __returnTrue
        else:
        __returnFalse
        ____self.file.close()
        
        Create Streaming object and authenticate*
        l = MyStreamListener()
        stream = tweepy.Stream(auth, l)
        
        This line filters Twitter Streams to capture data by keywords:*
        stream.filter(track=['apples', 'oranges'])
- - - - produces next value when applied to the iterator
    - - print(*it)
    - - for key, value in pythonistas.items()
    - - creates an iteratos when applied to an iterable
    - - file = open('file.txt')
        it = iter(file)
        print(next(it))
- - - - list
        
        for index,values in enumerate(data):
      - char
        
        for c in "texto":
      - dictionnary
        
        for key,val in dictionnary.items():
      - numpy arrays
        
        for val in array: -> gets columns
        
        for val in np.nditer(array): gets values
      - dataframes
        
        for label,row in dataframe.iterrows(): -> gets observations
- - - - METHODS
        
        .capitalize()
        
        replace("z","s")
    - - SUBSETTING
        
        x[4]
        x[-1]
        x[2:6] -> 2,3,4,5
      - FUNCTIONS
        
        Deleting elements:
        del(x[2])
        
        Adding elements:
        x + [2 , 3]
        
        Copying:
        y = list(x) o
        y= x[:]
        
        Pointing:
        y=x
      - METHODS
        
        .max()
        
        .len()
        
        .index("Precio")
        
        .reverse()
        
        .count("pepe")
        
        .append("nuevo")
    - - FUNCTIONS
        
        "text" in dictionnaty
        
        del(x["column"])
      - METHODS
        
        .keys()
        
        .values
    - - ATTRIBUTES
        
        .index = ["a", "b", "c"]
        
        .concat[list of dataframes]
      - SUBSETTING
        
        data["country"]-> pandas.core.series.Series
        
        data[["countries"]] -> DataFrame
        
        ROW ACCESS :
        
        data[1:4]
        
        LABEL based:
        
        data.loc[["country"]] -> array
        
        data.loc["country"] -> Series
        
        data.loc[["RU", "IN"], ["country","state"]]
        
        data.loc[:, ["country","state"]]
        
        POSITION based:
        
        ROW
        
        data.iloc[[1,2,3]]
        
        ROW & COLUMN
        
        data.iloc[[1,2,3],[0,1]]
        
        COLUMN
        
        data.iloc[:,[0,1]]
      - METHODS
        
        df["column"].apply(fun)
        
        .sortvalues("column", ascending=True)
        
        .info()
        
        df["column"].unique()
        
        df["column"].idxmax()
        
        .set_index("column")
        
        df["column"].nlargest(n=5)
        
        .div(1000)
        
        .index.tolist()
  - - - array()
        
        contain one type of data only
        
        operations element by element
        
        METHODS
        
        np.shape
        
        SUBSETTING
        
        x[2:3][4:7]
        x[2:3,4:7]
      - FUNCTIONS
        
        np.mean(x)
        
        np.median(x)
        
        np.corrcoef(x,y)
        
        np.std(x)
        
        np.sort(x)
        
        np.sum(x)
        
        np.random.normal(mean,std,no.samples)
        
        np.column_stack(x,y)
        
        np.random.seed(123)
        
        np.random.rand()
        
        np.random.randint(start,end)
    - - .pyplot
        
        FUNCTIONS
        
        .show()
        
        .plot(x,y)
        
        .scatter(x,y)
        
        .hist(x, bins=20)
        
        .xlabel("titx")
        
        .ylabel("ytit")
        
        .title("title")
        
        .yticks(values,names)
    - - FUNCTIONS
        
        pd.read_csv("file.csv", index_col=0, na_values='n/a', parse_dates=['Last Upadate'])
        
        pd.info()
    - - FUNCTIONS
        
        sns.set(color_codes=True)
        ax = sns.barplot(cd, [clinton, trump, sanders, cruz])
        ax.set(ylabel="count")
        plt.show()
    - - FUNCTIONS
        
        stock_prices = DataReader(ticker, data_source, start, end)