Python pandas.Series方法代码示例

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import Series [as 别名]
def average_true_range(df, n):
    """
    
    :param df: pandas.DataFrame
    :param n: 
    :return: pandas.DataFrame
    """
    i = 0
    TR_l = [0]
    while i < df.index[-1]:
        TR = max(df.loc[i + 1, 'High'], df.loc[i, 'Close']) - min(df.loc[i + 1, 'Low'], df.loc[i, 'Close'])
        TR_l.append(TR)
        i = i + 1
    TR_s = pd.Series(TR_l)
    ATR = pd.Series(TR_s.ewm(span=n, min_periods=n).mean(), name='ATR_' + str(n))
    df = df.join(ATR)
    return df 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import Series [as 别名]
def create_scats(self, varieties):
        self.scats = pd.DataFrame(columns=["x", "y", "color", "marker", "var"])
        for i, var in enumerate(varieties):
            self.legend.append(var)
            (x_array, y_array) = self.get_arrays(varieties, var)
            if len(x_array) <= 0:  # no data to graph!
                '''
                I am creating a single "position" for an agent that cannot
                be seen. This seems to fix the issue of colors being
                missmatched in the occasion that a group has no agents.
                '''
                x_array = [-1]
                y_array = [-1]
            elif len(x_array) != len(y_array):
                logging.debug("Array length mismatch in scatter plot")
                return
            color = get_color(varieties[var], i)
            marker = get_marker(varieties[var], i)
            scat = pd.DataFrame({"x": pd.Series(x_array),
                                 "y": pd.Series(y_array),
                                 "color": color,
                                 "marker": marker,
                                 "var": var})
            self.scats = self.scats.append(scat, ignore_index=True,
                                           sort=False) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import Series [as 别名]
def get_topn_topm(self, s1, s2, n=10, m=3):
        s1_sorted=s1.sort_values(ascending=False)
        s1topn_index=s1_sorted.index[:n]
        d=dict()
        for i in s1topn_index:
            d[i[:-3]]=s2[i[:-3]+'wn']
        s=pd.Series(d)
        s_sorted=s.sort_values(ascending=False)
        l=len(s_sorted[s_sorted!=0])
        if(l==0):
            index=[]
            for i in range(m):
                index.append(s1topn_index[i][:-3])
            return index
        elif(l<m):
            return s_sorted.index[:l]
        else:
            return s_sorted.index[:m] 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import Series [as 别名]
def ppsr(df):
    """Calculate Pivot Points, Supports and Resistances for given data
    
    :param df: pandas.DataFrame
    :return: pandas.DataFrame
    """
    PP = pd.Series((df['High'] + df['Low'] + df['Close']) / 3)
    R1 = pd.Series(2 * PP - df['Low'])
    S1 = pd.Series(2 * PP - df['High'])
    R2 = pd.Series(PP + df['High'] - df['Low'])
    S2 = pd.Series(PP - df['High'] + df['Low'])
    R3 = pd.Series(df['High'] + 2 * (PP - df['Low']))
    S3 = pd.Series(df['Low'] - 2 * (df['High'] - PP))
    psr = {'PP': PP, 'R1': R1, 'S1': S1, 'R2': R2, 'S2': S2, 'R3': R3, 'S3': S3}
    PSR = pd.DataFrame(psr)
    df = df.join(PSR)
    return df 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import Series [as 别名]
def trix(df, n):
    """Calculate TRIX for given data.
    
    :param df: pandas.DataFrame
    :param n: 
    :return: pandas.DataFrame
    """
    EX1 = df['Close'].ewm(span=n, min_periods=n).mean()
    EX2 = EX1.ewm(span=n, min_periods=n).mean()
    EX3 = EX2.ewm(span=n, min_periods=n).mean()
    i = 0
    ROC_l = [np.nan]
    while i + 1 <= df.index[-1]:
        ROC = (EX3[i + 1] - EX3[i]) / EX3[i]
        ROC_l.append(ROC)
        i = i + 1
    Trix = pd.Series(ROC_l, name='Trix_' + str(n))
    df = df.join(Trix)
    return df 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import Series [as 别名]
def vortex_indicator(df, n):
    """Calculate the Vortex Indicator for given data.
    
    Vortex Indicator described here:
        http://www.vortexindicator.com/VFX_VORTEX.PDF
    :param df: pandas.DataFrame
    :param n: 
    :return: pandas.DataFrame
    """
    i = 0
    TR = [0]
    while i < df.index[-1]:
        Range = max(df.loc[i + 1, 'High'], df.loc[i, 'Close']) - min(df.loc[i + 1, 'Low'], df.loc[i, 'Close'])
        TR.append(Range)
        i = i + 1
    i = 0
    VM = [0]
    while i < df.index[-1]:
        Range = abs(df.loc[i + 1, 'High'] - df.loc[i, 'Low']) - abs(df.loc[i + 1, 'Low'] - df.loc[i, 'High'])
        VM.append(Range)
        i = i + 1
    VI = pd.Series(pd.Series(VM).rolling(n).sum() / pd.Series(TR).rolling(n).sum(), name='Vortex_' + str(n))
    df = df.join(VI)
    return df 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import Series [as 别名]
def true_strength_index(df, r, s):
    """Calculate True Strength Index (TSI) for given data.
    
    :param df: pandas.DataFrame
    :param r: 
    :param s: 
    :return: pandas.DataFrame
    """
    M = pd.Series(df['Close'].diff(1))
    aM = abs(M)
    EMA1 = pd.Series(M.ewm(span=r, min_periods=r).mean())
    aEMA1 = pd.Series(aM.ewm(span=r, min_periods=r).mean())
    EMA2 = pd.Series(EMA1.ewm(span=s, min_periods=s).mean())
    aEMA2 = pd.Series(aEMA1.ewm(span=s, min_periods=s).mean())
    TSI = pd.Series(EMA2 / aEMA2, name='TSI_' + str(r) + '_' + str(s))
    df = df.join(TSI)
    return df 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import Series [as 别名]
def money_flow_index(df, n):
    """Calculate Money Flow Index and Ratio for given data.
    
    :param df: pandas.DataFrame
    :param n: 
    :return: pandas.DataFrame
    """
    PP = (df['High'] + df['Low'] + df['Close']) / 3
    i = 0
    PosMF = [0]
    while i < df.index[-1]:
        if PP[i + 1] > PP[i]:
            PosMF.append(PP[i + 1] * df.loc[i + 1, 'Volume'])
        else:
            PosMF.append(0)
        i = i + 1
    PosMF = pd.Series(PosMF)
    TotMF = PP * df['Volume']
    MFR = pd.Series(PosMF / TotMF)
    MFI = pd.Series(MFR.rolling(n, min_periods=n).mean(), name='MFI_' + str(n))
    df = df.join(MFI)
    return df 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import Series [as 别名]
def on_balance_volume(df, n):
    """Calculate On-Balance Volume for given data.
    
    :param df: pandas.DataFrame
    :param n: 
    :return: pandas.DataFrame
    """
    i = 0
    OBV = [0]
    while i < df.index[-1]:
        if df.loc[i + 1, 'Close'] - df.loc[i, 'Close'] > 0:
            OBV.append(df.loc[i + 1, 'Volume'])
        if df.loc[i + 1, 'Close'] - df.loc[i, 'Close'] == 0:
            OBV.append(0)
        if df.loc[i + 1, 'Close'] - df.loc[i, 'Close'] < 0:
            OBV.append(-df.loc[i + 1, 'Volume'])
        i = i + 1
    OBV = pd.Series(OBV)
    OBV_ma = pd.Series(OBV.rolling(n, min_periods=n).mean(), name='OBV_' + str(n))
    df = df.join(OBV_ma)
    return df 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import Series [as 别名]
def coppock_curve(df, n):
    """Calculate Coppock Curve for given data.
    
    :param df: pandas.DataFrame
    :param n: 
    :return: pandas.DataFrame
    """
    M = df['Close'].diff(int(n * 11 / 10) - 1)
    N = df['Close'].shift(int(n * 11 / 10) - 1)
    ROC1 = M / N
    M = df['Close'].diff(int(n * 14 / 10) - 1)
    N = df['Close'].shift(int(n * 14 / 10) - 1)
    ROC2 = M / N
    Copp = pd.Series((ROC1 + ROC2).ewm(span=n, min_periods=n).mean(), name='Copp_' + str(n))
    df = df.join(Copp)
    return df 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import Series [as 别名]
def keltner_channel(df, n):
    """Calculate Keltner Channel for given data.
    
    :param df: pandas.DataFrame
    :param n: 
    :return: pandas.DataFrame
    """
    KelChM = pd.Series(((df['High'] + df['Low'] + df['Close']) / 3).rolling(n, min_periods=n).mean(),
                       name='KelChM_' + str(n))
    KelChU = pd.Series(((4 * df['High'] - 2 * df['Low'] + df['Close']) / 3).rolling(n, min_periods=n).mean(),
                       name='KelChU_' + str(n))
    KelChD = pd.Series(((-2 * df['High'] + 4 * df['Low'] + df['Close']) / 3).rolling(n, min_periods=n).mean(),
                       name='KelChD_' + str(n))
    df = df.join(KelChM)
    df = df.join(KelChU)
    df = df.join(KelChD)
    return df 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import Series [as 别名]
def ultimate_oscillator(df):
    """Calculate Ultimate Oscillator for given data.
    
    :param df: pandas.DataFrame
    :return: pandas.DataFrame
    """
    i = 0
    TR_l = [0]
    BP_l = [0]
    while i < df.index[-1]:
        TR = max(df.loc[i + 1, 'High'], df.loc[i, 'Close']) - min(df.loc[i + 1, 'Low'], df.loc[i, 'Close'])
        TR_l.append(TR)
        BP = df.loc[i + 1, 'Close'] - min(df.loc[i + 1, 'Low'], df.loc[i, 'Close'])
        BP_l.append(BP)
        i = i + 1
    UltO = pd.Series((4 * pd.Series(BP_l).rolling(7).sum() / pd.Series(TR_l).rolling(7).sum()) + (
                2 * pd.Series(BP_l).rolling(14).sum() / pd.Series(TR_l).rolling(14).sum()) + (
                                 pd.Series(BP_l).rolling(28).sum() / pd.Series(TR_l).rolling(28).sum()),
                     name='Ultimate_Osc')
    df = df.join(UltO)
    return df 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import Series [as 别名]
def donchian_channel(df, n):
    """Calculate donchian channel of given pandas data frame.
    :param df: pandas.DataFrame
    :param n:
    :return: pandas.DataFrame
    """
    i = 0
    dc_l = []
    while i < n - 1:
        dc_l.append(0)
        i += 1

    i = 0
    while i + n - 1 < df.index[-1]:
        dc = max(df['High'].ix[i:i + n - 1]) - min(df['Low'].ix[i:i + n - 1])
        dc_l.append(dc)
        i += 1

    donchian_chan = pd.Series(dc_l, name='Donchian_' + str(n))
    donchian_chan = donchian_chan.shift(n - 1)
    return df.join(donchian_chan) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import Series [as 别名]
def _get_target_encoder(self, x, y):
        """Return a mapping from categories to average target values.

        Args:
            x (pandas.Series): a categorical column to encode.
            y (pandas.Series): the target column

        Returns:
            (dict): mapping from categories to average target values
        """

        assert len(x) == len(y)

        # NaN cannot be used as a key for dict. So replace it with a random
        # integer
        mean_count = pd.DataFrame({y.name: y, x.name: x.fillna(NAN_INT)}).groupby(x.name)[y.name].agg(['mean', 'count'])
        smoothing = 1 / (1 + np.exp(-(mean_count['count'] - self.min_samples) / self.smoothing))

        mean_count[y.name] = self.target_mean * (1 - smoothing) + mean_count['mean'] * smoothing
        return mean_count[y.name].to_dict() 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import Series [as 别名]
def fit(self, X, y):
        """Encode categorical columns into average target values.

        Args:
            X (pandas.DataFrame): categorical columns to encode
            y (pandas.Series): the target column

        Returns:
            (pandas.DataFrame): encoded columns
        """
        self.target_encoders = [None] * X.shape[1]
        self.target_mean = y.mean()

        for i, col in enumerate(X.columns):
            if self.cv is None:
                self.target_encoders[i] = self._get_target_encoder(X[col], y)
            else:
                self.target_encoders[i] = []
                for i_cv, (i_trn, i_val) in enumerate(self.cv.split(X[col], y), 1):
                    self.target_encoders[i].append(self._get_target_encoder(X.loc[i_trn, col], y[i_trn]))

        return self