++

5 hours ago · 19c147c107
parent a7ab5d48c9
commit 19c147c107
3 changed files with 1370 additions and 0 deletions
--- a/load_optrators.py
+++ b/load_optrators.py
@ -0,0 +1,24 @@
 # 将手动保存的操作符, 输出为可以直接在提示词使用的格式
 # 操作符不用爬虫, 因为只有一页, 直接在网页复制
 import json
 import os
 current_dir = os.path.dirname(os.path.abspath(__file__))
 opreator_file = os.path.join(current_dir, 'operators.json')
 with open(opreator_file, 'r') as f:
    optrators = json.load(f)
 optput = ""
 for optrator in optrators:
    name = optrator.get("name").replace("\n", "").replace("\r", "")
    description = optrator.get("description").replace("\n", "").replace("\r", "")
    category = optrator.get("category").replace("\n", "").replace("\r", "")
    definition = optrator.get("definition").replace("\n", "").replace("\r", "")
    optput += f"name: {name}\ndescription: {description}\ncategory:{category}\ndefinition:{definition}\n\n"
    # print(f"name: {name}\ndescription: {description}\ncategory:{category}\ndefinition:{definition}\n")
 with open("operators.txt", "w") as f:
    f.write(optput)
--- a/operators.json
+++ b/operators.json
@ -0,0 +1,926 @@
 [
    {
        "name": "add",
        "category": "Arithmetic",
        "scope": [
            "REGULAR"
        ],
        "definition": "add(x, y, filter = false), x + y",
        "description": "Add all inputs (at least 2 inputs required). If filter = true, filter all input NaN to 0 before adding",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "abs",
        "category": "Arithmetic",
        "scope": [
            "REGULAR"
        ],
        "definition": "abs(x)",
        "description": "Absolute value of x",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "log",
        "category": "Arithmetic",
        "scope": [
            "REGULAR"
        ],
        "definition": "log(x)",
        "description": "Natural logarithm. For example: Log(high/low) uses natural logarithm of high/low ratio as stock weights.",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "subtract",
        "category": "Arithmetic",
        "scope": [
            "REGULAR"
        ],
        "definition": "subtract(x, y, filter=false), x - y",
        "description": "x-y. If filter = true, filter all input NaN to 0 before subtracting",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "signed_power",
        "category": "Arithmetic",
        "scope": [
            "REGULAR"
        ],
        "definition": "signed_power(x, y)",
        "description": "x raised to the power of y such that final result preserves sign of x",
        "documentation": "/operators/signed_power",
        "level": "ALL"
    },
    {
        "name": "sign",
        "category": "Arithmetic",
        "scope": [
            "REGULAR"
        ],
        "definition": "sign(x)",
        "description": "if input > 0, return 1; if input < 0, return -1; if input = 0, return 0; if input = NaN, return NaN;\r\n\r\nInput: Value of 7 instruments at day t: (2, -3, 5, 6, 3, NaN, -10)\r\nOutput: (1, -1, 1, 1, 1, NaN, -1)",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "reverse",
        "category": "Arithmetic",
        "scope": [
            "REGULAR"
        ],
        "definition": "reverse(x)",
        "description": " - x",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "power",
        "category": "Arithmetic",
        "scope": [
            "REGULAR"
        ],
        "definition": "power(x, y)",
        "description": "x ^ y",
        "documentation": "/operators/power",
        "level": "ALL"
    },
    {
        "name": "multiply",
        "category": "Arithmetic",
        "scope": [
            "REGULAR"
        ],
        "definition": "multiply(x ,y, ... , filter=false), x * y",
        "description": "Multiply all inputs. At least 2 inputs are required. Filter sets the NaN values to 1",
        "documentation": "/operators/multiply",
        "level": "ALL"
    },
    {
        "name": "min",
        "category": "Arithmetic",
        "scope": [
            "REGULAR"
        ],
        "definition": "min(x, y ..)",
        "description": "Minimum value of all inputs. At least 2 inputs are required",
        "documentation": "/operators/min",
        "level": "ALL"
    },
    {
        "name": "max",
        "category": "Arithmetic",
        "scope": [
            "REGULAR"
        ],
        "definition": "max(x, y, ..)",
        "description": "Maximum value of all inputs. At least 2 inputs are required",
        "documentation": "/operators/max",
        "level": "ALL"
    },
    {
        "name": "inverse",
        "category": "Arithmetic",
        "scope": [
            "REGULAR"
        ],
        "definition": "inverse(x)",
        "description": "1 / x",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "sqrt",
        "category": "Arithmetic",
        "scope": [
            "REGULAR"
        ],
        "definition": "sqrt(x)",
        "description": "Square root of x",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "s_log_1p",
        "category": "Arithmetic",
        "scope": [
            "REGULAR"
        ],
        "definition": "s_log_1p(x)",
        "description": "Confine function to a shorter range using logarithm such that higher input remains higher and negative input remains negative as an output of resulting function and -1 or 1 is an asymptotic value",
        "documentation": "/operators/s_log_1p",
        "level": null
    },
    {
        "name": "densify",
        "category": "Arithmetic",
        "scope": [
            "REGULAR"
        ],
        "definition": "densify(x)",
        "description": "Converts a grouping field of many buckets into lesser number of only available buckets so as to make working with grouping fields computationally efficient",
        "documentation": "/operators/densify",
        "level": "ALL"
    },
    {
        "name": "divide",
        "category": "Arithmetic",
        "scope": [
            "REGULAR"
        ],
        "definition": "divide(x, y), x / y",
        "description": "x / y",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "not",
        "category": "Logical",
        "scope": [
            "REGULAR"
        ],
        "definition": "not(x)",
        "description": "Returns the logical negation of x. If x is true (1), it returns false (0), and if input is false (0), it returns true (1).",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "and",
        "category": "Logical",
        "scope": [
            "REGULAR"
        ],
        "definition": "and(input1, input2)",
        "description": "Logical AND operator, returns true if both operands are true and returns false otherwise",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "less",
        "category": "Logical",
        "scope": [
            "REGULAR"
        ],
        "definition": "input1 < input2",
        "description": "If input1 < input2 return true, else return false",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "equal",
        "category": "Logical",
        "scope": [
            "REGULAR"
        ],
        "definition": "input1 == input2",
        "description": "Returns true if both inputs are same and returns false otherwise",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "or",
        "category": "Logical",
        "scope": [
            "REGULAR"
        ],
        "definition": "or(input1, input2)",
        "description": "Logical OR operator returns true if either or both inputs are true and returns false otherwise",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "not_equal",
        "category": "Logical",
        "scope": [
            "REGULAR"
        ],
        "definition": "input1!= input2",
        "description": "Returns true if both inputs are NOT the same and returns false otherwise",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "greater",
        "category": "Logical",
        "scope": [
            "REGULAR"
        ],
        "definition": "input1 > input2",
        "description": "Logic comparison operators to compares two inputs",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "greater_equal",
        "category": "Logical",
        "scope": [
            "REGULAR"
        ],
        "definition": "input1 >= input2",
        "description": "Returns true if input1 >= input2, return false otherwise",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "less_equal",
        "category": "Logical",
        "scope": [
            "REGULAR"
        ],
        "definition": "input1 <= input2",
        "description": "Returns true if input1 <= input2, return false otherwise",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "is_nan",
        "category": "Logical",
        "scope": [
            "REGULAR"
        ],
        "definition": "is_nan(input)",
        "description": "If (input == NaN) return 1 else return 0",
        "documentation": "/operators/is_nan",
        "level": "ALL"
    },
    {
        "name": "if_else",
        "category": "Logical",
        "scope": [
            "REGULAR"
        ],
        "definition": "if_else(input1, input2, input 3)",
        "description": "If input1 is true then return input2 else return input3.",
        "documentation": "/operators/if_else",
        "level": "ALL"
    },
    {
        "name": "ts_sum",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_sum(x, d)",
        "description": "Sum values of x for the past d days.",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "ts_scale",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_scale(x, d, constant = 0)",
        "description": "Returns (x - ts_min(x, d)) / (ts_max(x, d) - ts_min(x, d)) + constant. This operator is similar to scale down operator but acts in time series space",
        "documentation": "/operators/ts_scale",
        "level": "ALL"
    },
    {
        "name": "ts_mean",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_mean(x, d)",
        "description": "Returns average value of x for the past d days.",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "ts_zscore",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_zscore(x, d)",
        "description": "Z-score is a numerical measurement that describes a value's relationship to the mean of a group of values. Z-score is measured in terms of standard deviations from the mean: (x - tsmean(x,d)) / tsstddev(x,d). This operator may help reduce outliers and drawdown.\r\n\r\nInput: Value of 1 instrument in past 5 days where first element is the latest: (100, 0, 50, 60, 25), d: 5\r\nOutput: (100-47)/33.7 = 1.57 from SD: 33.7, mean = 47",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "ts_std_dev",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_std_dev(x, d)",
        "description": "Returns standard deviation of x for the past d days",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "kth_element",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "kth_element(x, d, k)",
        "description": "Returns K-th valid value of input by looking through lookback days. This operator can be used to backfill missing data if k=1",
        "documentation": "/operators/kth_element",
        "level": "ALL"
    },
    {
        "name": "inst_tvr",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "inst_tvr(x, d)",
        "description": "Total trading value / Total holding value in the past d days\r\n\r\nInput: Value of 1 instrument in past 5 days where first element is the latest: (105, 102, 99, 101,100)\r\nOutput: 0.022 from (1+2+3+3)/(105+102+99+101)",
        "documentation": null,
        "level": null
    },
    {
        "name": "ts_corr",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_corr(x, y, d)",
        "description": "Returns correlation of x and y for the past d days",
        "documentation": "/operators/ts_corr",
        "level": "ALL"
    },
    {
        "name": "ts_count_nans",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_count_nans(x ,d)",
        "description": "Returns the number of NaN values in x for the past d days\r\n\r\nInput: Value of 1 instrument in past 4 days where first element is the latest: (100, NaN, NaN, 200), d: 4\r\nOutput: Number of NaN in 4 days = 2",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "ts_target_tvr_decay",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_target_tvr_decay(x, lambda_min=0, lambda_max=1, target_tvr=0.1)",
        "description": "Tune \"ts_decay\" to have a turnover equal to a certain target, with optimization weight range between lambda_min, lambda_max",
        "documentation": null,
        "level": null
    },
    {
        "name": "ts_median",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_median(x, d)",
        "description": "Returns median value of x for the past d days",
        "documentation": null,
        "level": null
    },
    {
        "name": "ts_covariance",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_covariance(y, x, d)",
        "description": "Returns covariance of y and x for the past d days",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "ts_decay_linear",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_decay_linear(x, d, dense = false)",
        "description": "Returns the linear decay on x for the past d days. Dense parameter=false means operator works in sparse mode and we treat NaN as 0. In dense mode we do not.",
        "documentation": "/operators/ts_decay_linear",
        "level": "ALL"
    },
    {
        "name": "ts_product",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_product(x, d)",
        "description": "Returns product of x for the past d days",
        "documentation": "/operators/ts_product",
        "level": "ALL"
    },
    {
        "name": "ts_regression",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_regression(y, x, d, lag = 0, rettype = 0)",
        "description": "Returns various parameters related to regression function",
        "documentation": "/operators/ts_regression",
        "level": "ALL"
    },
    {
        "name": "ts_delta_limit",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_delta_limit(x, y, limit_volume=0.1)",
        "description": "Limit the change in the Alpha position x between dates to a specified fraction of y. The \"limit_volume\" can be in the range of 0 to 1. Also, please be aware of the scaling for x and y. Besides setting y as adv20 or volume related data, you can also set y as a constant.",
        "documentation": null,
        "level": null
    },
    {
        "name": "ts_step",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_step(1)",
        "description": "Returns days' counter",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "ts_decay_exp_window",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_decay_exp_window(x, d, factor = f)",
        "description": "Returns exponential decay of x with smoothing factor for the past d days",
        "documentation": "/operators/ts_decay_exp_window",
        "level": null
    },
    {
        "name": "ts_quantile",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_quantile(x,d, driver=\"gaussian\" )",
        "description": "It calculates ts_rank and apply to its value an inverse cumulative density function from driver distribution. Possible values of driver (optional ) are \"gaussian\", \"uniform\", \"cauchy\" distribution where \"gaussian\" is the default.\r\n\r\nInput: Value of 1 instrument in past 7 days where first element is the latest: (8, 10, 4, 6, 5, 3, 2), d: 7, driver: ’gaussian’\r\nOutput: quantile = 0.82 from SD = 2.82, mean = 5.43, zscore = 0.911",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "days_from_last_change",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "days_from_last_change(x)",
        "description": "Amount of days since last change of x\r\n\r\nInput: Value of 1 instrument in past 7 days where first element is the latest: (2, 2, 2, 7, 5, 16, 1)\r\nOutput: 3",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "hump",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "hump(x, hump = 0.01)",
        "description": "Limits amount and magnitude of changes in input (thus reducing turnover)",
        "documentation": "/operators/hump",
        "level": "ALL"
    },
    {
        "name": "last_diff_value",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "last_diff_value(x, d)",
        "description": "Returns last x value not equal to current x value from last d days",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "ts_arg_max",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_arg_max(x, d)",
        "description": "Returns the relative index of the max value in the time series for the past d days. If the current day has the max value for the past d days, it returns 0. If previous day has the max value for the past d days, it returns 1",
        "documentation": "/operators/ts_arg_max",
        "level": "ALL"
    },
    {
        "name": "ts_arg_min",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_arg_min(x, d)",
        "description": "Returns the relative index of the min value in the time series for the past d days; If the current day has the min value for the past d days, it returns 0; If previous day has the min value for the past d days, it returns 1.",
        "documentation": "/operators/ts_arg_min",
        "level": "ALL"
    },
    {
        "name": "ts_av_diff",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_av_diff(x, d)",
        "description": "Returns x - tsmean(x, d), but deals with NaNs carefully. That is NaNs are ignored during mean computation",
        "documentation": "/operators/ts_av_diff",
        "level": "ALL"
    },
    {
        "name": "ts_backfill",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_backfill(x, d)",
        "description": "Returns the first valid value of the input x by looking through lookback days (d). This operator can be used to backfill missing data.",
        "documentation": "/operators/ts_backfill",
        "level": "ALL"
    },
    {
        "name": "ts_rank",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_rank(x, d, constant = 0)",
        "description": "Rank the values of x for each instrument over the past d days, then return the rank of the current value + constant. If not specified, by default, constant = 0.\r\n\r\nInput: Value of 1 instrument in past 3 days where first element is the latest: (100, 0, 200), d: 3\r\nOutput: 0.5",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "ts_delay",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_delay(x, d)",
        "description": "Returns x value d days ago\r\n\r\nInput: Value of 1 instrument in past 7 days where first element is the latest: (2, 3, 5, 6, 3, 8, 10), d: 6\r\nOutput: Value 6 days ago = 10",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "ts_delta",
        "category": "Time Series",
        "scope": [
            "REGULAR"
        ],
        "definition": "ts_delta(x, d)",
        "description": "Returns x - ts_delay(x, d)\r\n\r\nInput: Value of 1 instrument in past 7 days where first element is the latest: (2, 3, 5, 6, 3, 8, 10), d: 6\r\nOutput: Value today – value 6 days ago = 2 - 10 = -8",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "winsorize",
        "category": "Cross Sectional",
        "scope": [
            "REGULAR"
        ],
        "definition": "winsorize(x, std=4)",
        "description": "Winsorizes x to make sure that all values in x are between the lower and upper limits, which are specified as multiple of std.\r\n\r\nInput: Value of 7 instruments at day t: (2, 4, 5, 6, 3, 8, 10), std: 1\r\nOutput: (2.81, 4, 5, 6, 3, 8, 8.03) from SD. = 2.61, mean = 5.42",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "truncate",
        "category": "Cross Sectional",
        "scope": [
            "REGULAR"
        ],
        "definition": "truncate(x,maxPercent=0.01)",
        "description": "Operator truncates all values of x to maxPercent. Here, maxPercent is in decimal notation",
        "documentation": "/operators/truncate",
        "level": null
    },
    {
        "name": "regression_neut",
        "category": "Cross Sectional",
        "scope": [
            "REGULAR"
        ],
        "definition": "regression_neut(y, x)",
        "description": "Conducts the cross-sectional regression on the stocks with Y as target and X as the independent variable",
        "documentation": "/operators/regression_neut",
        "level": null
    },
    {
        "name": "scale",
        "category": "Cross Sectional",
        "scope": [
            "REGULAR"
        ],
        "definition": "scale(x, scale=1, longscale=1, shortscale=1)",
        "description": "Scales input to booksize. We can also scale the long positions and short positions to separate scales by mentioning additional parameters to the operator",
        "documentation": "/operators/scale",
        "level": "ALL"
    },
    {
        "name": "rank",
        "category": "Cross Sectional",
        "scope": [
            "REGULAR"
        ],
        "definition": "rank(x, rate=2)",
        "description": "Ranks the input among all the instruments and returns an equally distributed number between 0.0 and 1.0. For precise sort, use the rate as 0",
        "documentation": "/operators/rank",
        "level": "ALL"
    },
    {
        "name": "quantile",
        "category": "Cross Sectional",
        "scope": [
            "REGULAR"
        ],
        "definition": "quantile(x, driver = gaussian, sigma = 1.0)",
        "description": "Rank the raw vector, shift the ranked Alpha vector, apply distribution (gaussian, cauchy, uniform). If driver is uniform, it simply subtract each Alpha value with the mean of all Alpha values in the Alpha vector",
        "documentation": "/operators/quantile",
        "level": "ALL"
    },
    {
        "name": "normalize",
        "category": "Cross Sectional",
        "scope": [
            "REGULAR"
        ],
        "definition": "normalize(x, useStd = false, limit = 0.0)",
        "description": "Calculates the mean value of all valid alpha values for a certain date, then subtracts that mean from each element",
        "documentation": "/operators/normalize",
        "level": "ALL"
    },
    {
        "name": "zscore",
        "category": "Cross Sectional",
        "scope": [
            "REGULAR"
        ],
        "definition": "zscore(x)",
        "description": "Z-score is a numerical measurement that describes a value's relationship to the mean of a group of values. Z-score is measured in terms of standard deviations from the mean",
        "documentation": "/operators/zscore",
        "level": "ALL"
    },
    {
        "name": "vec_min",
        "category": "Vector",
        "scope": [
            "REGULAR"
        ],
        "definition": "vec_min(x)",
        "description": "Minimum value form vector field x",
        "documentation": null,
        "level": null
    },
    {
        "name": "vec_count",
        "category": "Vector",
        "scope": [
            "REGULAR"
        ],
        "definition": "vec_count(x)",
        "description": "Number of elements in vector field x",
        "documentation": null,
        "level": null
    },
    {
        "name": "vec_stddev",
        "category": "Vector",
        "scope": [
            "REGULAR"
        ],
        "definition": "vec_stddev(x)",
        "description": "Standard Deviation of vector field x",
        "documentation": null,
        "level": null
    },
    {
        "name": "vec_range",
        "category": "Vector",
        "scope": [
            "REGULAR"
        ],
        "definition": "vec_range(x)",
        "description": "Difference between maximum and minimum element in vector field x",
        "documentation": null,
        "level": null
    },
    {
        "name": "vec_avg",
        "category": "Vector",
        "scope": [
            "REGULAR"
        ],
        "definition": "vec_avg(x)",
        "description": "Taking mean of the vector field x\r\n\r\nInput: Vector of value of 1 instrument in a day: (2, 3, 5, 6, 3, 8, 10)\r\nOutput: 37 / 7 = 5.29",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "vec_sum",
        "category": "Vector",
        "scope": [
            "REGULAR"
        ],
        "definition": "vec_sum(x)",
        "description": "Sum of vector field x\r\n\r\nInput: Vector of value of 1 instrument in a day: (2, 3, 5, 6, 3, 8, 10)\r\nOutput: 2 + 3 + 5 + 6 + 3 + 8 + 10 = 37",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "vec_max",
        "category": "Vector",
        "scope": [
            "REGULAR"
        ],
        "definition": "vec_max(x)",
        "description": "Maximum value form vector field x",
        "documentation": null,
        "level": null
    },
    {
        "name": "left_tail",
        "category": "Transformational",
        "scope": [
            "REGULAR"
        ],
        "definition": "left_tail(x, maximum = 0)",
        "description": "NaN everything greater than maximum, maximum should be constant",
        "documentation": "/operators/left_tail",
        "level": null
    },
    {
        "name": "trade_when",
        "category": "Transformational",
        "scope": [
            "REGULAR"
        ],
        "definition": "trade_when(x, y, z)",
        "description": "Used in order to change Alpha values only under a specified condition and to hold Alpha values in other cases. It also allows to close Alpha positions (assign NaN values) under a specified condition",
        "documentation": "/operators/trade_when",
        "level": "ALL"
    },
    {
        "name": "right_tail",
        "category": "Transformational",
        "scope": [
            "REGULAR"
        ],
        "definition": "right_tail(x, minimum = 0)",
        "description": "NaN everything less than minimum, minimum should be constant",
        "documentation": "/operators/right_tail",
        "level": null
    },
    {
        "name": "bucket",
        "category": "Transformational",
        "scope": [
            "REGULAR"
        ],
        "definition": "bucket(rank(x), range=\"0, 1, 0.1\" or buckets = \"2,5,6,7,10\")",
        "description": "Convert float values into indexes for user-specified buckets. Bucket is useful for creating group values, which can be passed to GROUP as input",
        "documentation": "/operators/bucket",
        "level": "ALL"
    },
    {
        "name": "group_rank",
        "category": "Group",
        "scope": [
            "REGULAR"
        ],
        "definition": "group_rank(x, group)",
        "description": "Each elements in a group is assigned the corresponding rank in this group",
        "documentation": "/operators/group_rank",
        "level": "ALL"
    },
    {
        "name": "group_cartesian_product",
        "category": "Group",
        "scope": [
            "REGULAR"
        ],
        "definition": "group_cartesian_product(g1, g2)",
        "description": "Merge two groups into one group. If originally there are len_1 and len_2 group indices in g1 and g2, there will be len_1 * len_2 indices in the new group.",
        "documentation": null,
        "level": null
    },
    {
        "name": "group_backfill",
        "category": "Group",
        "scope": [
            "REGULAR"
        ],
        "definition": "group_backfill(x, group, d, std = 4.0)",
        "description": "If a certain value for a certain date and instrument is NaN, from the set of same group instruments, calculate winsorized mean of all non-NaN values over last d days",
        "documentation": "/operators/group_backfill",
        "level": "ALL"
    },
    {
        "name": "group_mean",
        "category": "Group",
        "scope": [
            "REGULAR"
        ],
        "definition": "group_mean(x, weight, group)",
        "description": "All elements in group equals to the mean",
        "documentation": "/operators/group_mean",
        "level": "ALL"
    },
    {
        "name": "group_neutralize",
        "category": "Group",
        "scope": [
            "REGULAR"
        ],
        "definition": "group_neutralize(x, group)",
        "description": "Neutralizes Alpha against groups. These groups can be subindustry, industry, sector, country or a constant",
        "documentation": "/operators/group_neutralize",
        "level": "ALL"
    },
    {
        "name": "group_normalize",
        "category": "Group",
        "scope": [
            "REGULAR"
        ],
        "definition": "group_normalize(x, group, constantCheck=False, tolerance=0.01, scale=1)",
        "description": "Normalizes input such that each group's absolute sum is 1",
        "documentation": null,
        "level": null
    },
    {
        "name": "group_median",
        "category": "Group",
        "scope": [
            "REGULAR"
        ],
        "definition": "group_median(x, group)",
        "description": "All elements in group equals to the median value of the group.",
        "documentation": null,
        "level": null
    },
    {
        "name": "group_scale",
        "category": "Group",
        "scope": [
            "REGULAR"
        ],
        "definition": "group_scale(x, group)",
        "description": "Normalizes the values in a group to be between 0 and 1. (x - groupmin) / (groupmax - groupmin)",
        "documentation": null,
        "level": "ALL"
    },
    {
        "name": "group_zscore",
        "category": "Group",
        "scope": [
            "REGULAR"
        ],
        "definition": "group_zscore(x, group)",
        "description": "Calculates group Z-score - numerical measurement that describes a value's relationship to the mean of a group of values. Z-score is measured in terms of standard deviations from the mean. zscore = (data - mean) / stddev of x for each instrument within its group.\r\n\r\nInput: Value of 5 instruments of Group A: (100, 0, 50, 60, 25)\r\nOutput: (1.57, -1.39, 0.09, 0.39, -0.65)",
        "documentation": null,
        "level": "ALL"
    }
 ]
--- a/operators.txt
+++ b/operators.txt
@ -0,0 +1,420 @@
 name: add
 description: Add all inputs (at least 2 inputs required). If filter = true, filter all input NaN to 0 before adding
 category:Arithmetic
 definition:add(x, y, filter = false), x + y
 name: abs
 description: Absolute value of x
 category:Arithmetic
 definition:abs(x)
 name: log
 description: Natural logarithm. For example: Log(high/low) uses natural logarithm of high/low ratio as stock weights.
 category:Arithmetic
 definition:log(x)
 name: subtract
 description: x-y. If filter = true, filter all input NaN to 0 before subtracting
 category:Arithmetic
 definition:subtract(x, y, filter=false), x - y
 name: signed_power
 description: x raised to the power of y such that final result preserves sign of x
 category:Arithmetic
 definition:signed_power(x, y)
 name: sign
 description: if input > 0, return 1; if input < 0, return -1; if input = 0, return 0; if input = NaN, return NaN;Input: Value of 7 instruments at day t: (2, -3, 5, 6, 3, NaN, -10)Output: (1, -1, 1, 1, 1, NaN, -1)
 category:Arithmetic
 definition:sign(x)
 name: reverse
 description:  - x
 category:Arithmetic
 definition:reverse(x)
 name: power
 description: x ^ y
 category:Arithmetic
 definition:power(x, y)
 name: multiply
 description: Multiply all inputs. At least 2 inputs are required. Filter sets the NaN values to 1
 category:Arithmetic
 definition:multiply(x ,y, ... , filter=false), x * y
 name: min
 description: Minimum value of all inputs. At least 2 inputs are required
 category:Arithmetic
 definition:min(x, y ..)
 name: max
 description: Maximum value of all inputs. At least 2 inputs are required
 category:Arithmetic
 definition:max(x, y, ..)
 name: inverse
 description: 1 / x
 category:Arithmetic
 definition:inverse(x)
 name: sqrt
 description: Square root of x
 category:Arithmetic
 definition:sqrt(x)
 name: s_log_1p
 description: Confine function to a shorter range using logarithm such that higher input remains higher and negative input remains negative as an output of resulting function and -1 or 1 is an asymptotic value
 category:Arithmetic
 definition:s_log_1p(x)
 name: densify
 description: Converts a grouping field of many buckets into lesser number of only available buckets so as to make working with grouping fields computationally efficient
 category:Arithmetic
 definition:densify(x)
 name: divide
 description: x / y
 category:Arithmetic
 definition:divide(x, y), x / y
 name: not
 description: Returns the logical negation of x. If x is true (1), it returns false (0), and if input is false (0), it returns true (1).
 category:Logical
 definition:not(x)
 name: and
 description: Logical AND operator, returns true if both operands are true and returns false otherwise
 category:Logical
 definition:and(input1, input2)
 name: less
 description: If input1 < input2 return true, else return false
 category:Logical
 definition:input1 < input2
 name: equal
 description: Returns true if both inputs are same and returns false otherwise
 category:Logical
 definition:input1 == input2
 name: or
 description: Logical OR operator returns true if either or both inputs are true and returns false otherwise
 category:Logical
 definition:or(input1, input2)
 name: not_equal
 description: Returns true if both inputs are NOT the same and returns false otherwise
 category:Logical
 definition:input1!= input2
 name: greater
 description: Logic comparison operators to compares two inputs
 category:Logical
 definition:input1 > input2
 name: greater_equal
 description: Returns true if input1 >= input2, return false otherwise
 category:Logical
 definition:input1 >= input2
 name: less_equal
 description: Returns true if input1 <= input2, return false otherwise
 category:Logical
 definition:input1 <= input2
 name: is_nan
 description: If (input == NaN) return 1 else return 0
 category:Logical
 definition:is_nan(input)
 name: if_else
 description: If input1 is true then return input2 else return input3.
 category:Logical
 definition:if_else(input1, input2, input 3)
 name: ts_sum
 description: Sum values of x for the past d days.
 category:Time Series
 definition:ts_sum(x, d)
 name: ts_scale
 description: Returns (x - ts_min(x, d)) / (ts_max(x, d) - ts_min(x, d)) + constant. This operator is similar to scale down operator but acts in time series space
 category:Time Series
 definition:ts_scale(x, d, constant = 0)
 name: ts_mean
 description: Returns average value of x for the past d days.
 category:Time Series
 definition:ts_mean(x, d)
 name: ts_zscore
 description: Z-score is a numerical measurement that describes a value's relationship to the mean of a group of values. Z-score is measured in terms of standard deviations from the mean: (x - tsmean(x,d)) / tsstddev(x,d). This operator may help reduce outliers and drawdown.Input: Value of 1 instrument in past 5 days where first element is the latest: (100, 0, 50, 60, 25), d: 5Output: (100-47)/33.7 = 1.57 from SD: 33.7, mean = 47
 category:Time Series
 definition:ts_zscore(x, d)
 name: ts_std_dev
 description: Returns standard deviation of x for the past d days
 category:Time Series
 definition:ts_std_dev(x, d)
 name: kth_element
 description: Returns K-th valid value of input by looking through lookback days. This operator can be used to backfill missing data if k=1
 category:Time Series
 definition:kth_element(x, d, k)
 name: inst_tvr
 description: Total trading value / Total holding value in the past d daysInput: Value of 1 instrument in past 5 days where first element is the latest: (105, 102, 99, 101,100)Output: 0.022 from (1+2+3+3)/(105+102+99+101)
 category:Time Series
 definition:inst_tvr(x, d)
 name: ts_corr
 description: Returns correlation of x and y for the past d days
 category:Time Series
 definition:ts_corr(x, y, d)
 name: ts_count_nans
 description: Returns the number of NaN values in x for the past d daysInput: Value of 1 instrument in past 4 days where first element is the latest: (100, NaN, NaN, 200), d: 4Output: Number of NaN in 4 days = 2
 category:Time Series
 definition:ts_count_nans(x ,d)
 name: ts_target_tvr_decay
 description: Tune "ts_decay" to have a turnover equal to a certain target, with optimization weight range between lambda_min, lambda_max
 category:Time Series
 definition:ts_target_tvr_decay(x, lambda_min=0, lambda_max=1, target_tvr=0.1)
 name: ts_median
 description: Returns median value of x for the past d days
 category:Time Series
 definition:ts_median(x, d)
 name: ts_covariance
 description: Returns covariance of y and x for the past d days
 category:Time Series
 definition:ts_covariance(y, x, d)
 name: ts_decay_linear
 description: Returns the linear decay on x for the past d days. Dense parameter=false means operator works in sparse mode and we treat NaN as 0. In dense mode we do not.
 category:Time Series
 definition:ts_decay_linear(x, d, dense = false)
 name: ts_product
 description: Returns product of x for the past d days
 category:Time Series
 definition:ts_product(x, d)
 name: ts_regression
 description: Returns various parameters related to regression function
 category:Time Series
 definition:ts_regression(y, x, d, lag = 0, rettype = 0)
 name: ts_delta_limit
 description: Limit the change in the Alpha position x between dates to a specified fraction of y. The "limit_volume" can be in the range of 0 to 1. Also, please be aware of the scaling for x and y. Besides setting y as adv20 or volume related data, you can also set y as a constant.
 category:Time Series
 definition:ts_delta_limit(x, y, limit_volume=0.1)
 name: ts_step
 description: Returns days' counter
 category:Time Series
 definition:ts_step(1)
 name: ts_decay_exp_window
 description: Returns exponential decay of x with smoothing factor for the past d days
 category:Time Series
 definition:ts_decay_exp_window(x, d, factor = f)
 name: ts_quantile
 description: It calculates ts_rank and apply to its value an inverse cumulative density function from driver distribution. Possible values of driver (optional ) are "gaussian", "uniform", "cauchy" distribution where "gaussian" is the default.Input: Value of 1 instrument in past 7 days where first element is the latest: (8, 10, 4, 6, 5, 3, 2), d: 7, driver: ’gaussian’Output: quantile = 0.82 from SD = 2.82, mean = 5.43, zscore = 0.911
 category:Time Series
 definition:ts_quantile(x,d, driver="gaussian" )
 name: days_from_last_change
 description: Amount of days since last change of xInput: Value of 1 instrument in past 7 days where first element is the latest: (2, 2, 2, 7, 5, 16, 1)Output: 3
 category:Time Series
 definition:days_from_last_change(x)
 name: hump
 description: Limits amount and magnitude of changes in input (thus reducing turnover)
 category:Time Series
 definition:hump(x, hump = 0.01)
 name: last_diff_value
 description: Returns last x value not equal to current x value from last d days
 category:Time Series
 definition:last_diff_value(x, d)
 name: ts_arg_max
 description: Returns the relative index of the max value in the time series for the past d days. If the current day has the max value for the past d days, it returns 0. If previous day has the max value for the past d days, it returns 1
 category:Time Series
 definition:ts_arg_max(x, d)
 name: ts_arg_min
 description: Returns the relative index of the min value in the time series for the past d days; If the current day has the min value for the past d days, it returns 0; If previous day has the min value for the past d days, it returns 1.
 category:Time Series
 definition:ts_arg_min(x, d)
 name: ts_av_diff
 description: Returns x - tsmean(x, d), but deals with NaNs carefully. That is NaNs are ignored during mean computation
 category:Time Series
 definition:ts_av_diff(x, d)
 name: ts_backfill
 description: Returns the first valid value of the input x by looking through lookback days (d). This operator can be used to backfill missing data.
 category:Time Series
 definition:ts_backfill(x, d)
 name: ts_rank
 description: Rank the values of x for each instrument over the past d days, then return the rank of the current value + constant. If not specified, by default, constant = 0.Input: Value of 1 instrument in past 3 days where first element is the latest: (100, 0, 200), d: 3Output: 0.5
 category:Time Series
 definition:ts_rank(x, d, constant = 0)
 name: ts_delay
 description: Returns x value d days agoInput: Value of 1 instrument in past 7 days where first element is the latest: (2, 3, 5, 6, 3, 8, 10), d: 6Output: Value 6 days ago = 10
 category:Time Series
 definition:ts_delay(x, d)
 name: ts_delta
 description: Returns x - ts_delay(x, d)Input: Value of 1 instrument in past 7 days where first element is the latest: (2, 3, 5, 6, 3, 8, 10), d: 6Output: Value today – value 6 days ago = 2 - 10 = -8
 category:Time Series
 definition:ts_delta(x, d)
 name: winsorize
 description: Winsorizes x to make sure that all values in x are between the lower and upper limits, which are specified as multiple of std.Input: Value of 7 instruments at day t: (2, 4, 5, 6, 3, 8, 10), std: 1Output: (2.81, 4, 5, 6, 3, 8, 8.03) from SD. = 2.61, mean = 5.42
 category:Cross Sectional
 definition:winsorize(x, std=4)
 name: truncate
 description: Operator truncates all values of x to maxPercent. Here, maxPercent is in decimal notation
 category:Cross Sectional
 definition:truncate(x,maxPercent=0.01)
 name: regression_neut
 description: Conducts the cross-sectional regression on the stocks with Y as target and X as the independent variable
 category:Cross Sectional
 definition:regression_neut(y, x)
 name: scale
 description: Scales input to booksize. We can also scale the long positions and short positions to separate scales by mentioning additional parameters to the operator
 category:Cross Sectional
 definition:scale(x, scale=1, longscale=1, shortscale=1)
 name: rank
 description: Ranks the input among all the instruments and returns an equally distributed number between 0.0 and 1.0. For precise sort, use the rate as 0
 category:Cross Sectional
 definition:rank(x, rate=2)
 name: quantile
 description: Rank the raw vector, shift the ranked Alpha vector, apply distribution (gaussian, cauchy, uniform). If driver is uniform, it simply subtract each Alpha value with the mean of all Alpha values in the Alpha vector
 category:Cross Sectional
 definition:quantile(x, driver = gaussian, sigma = 1.0)
 name: normalize
 description: Calculates the mean value of all valid alpha values for a certain date, then subtracts that mean from each element
 category:Cross Sectional
 definition:normalize(x, useStd = false, limit = 0.0)
 name: zscore
 description: Z-score is a numerical measurement that describes a value's relationship to the mean of a group of values. Z-score is measured in terms of standard deviations from the mean
 category:Cross Sectional
 definition:zscore(x)
 name: vec_min
 description: Minimum value form vector field x
 category:Vector
 definition:vec_min(x)
 name: vec_count
 description: Number of elements in vector field x
 category:Vector
 definition:vec_count(x)
 name: vec_stddev
 description: Standard Deviation of vector field x
 category:Vector
 definition:vec_stddev(x)
 name: vec_range
 description: Difference between maximum and minimum element in vector field x
 category:Vector
 definition:vec_range(x)
 name: vec_avg
 description: Taking mean of the vector field xInput: Vector of value of 1 instrument in a day: (2, 3, 5, 6, 3, 8, 10)Output: 37 / 7 = 5.29
 category:Vector
 definition:vec_avg(x)
 name: vec_sum
 description: Sum of vector field xInput: Vector of value of 1 instrument in a day: (2, 3, 5, 6, 3, 8, 10)Output: 2 + 3 + 5 + 6 + 3 + 8 + 10 = 37
 category:Vector
 definition:vec_sum(x)
 name: vec_max
 description: Maximum value form vector field x
 category:Vector
 definition:vec_max(x)
 name: left_tail
 description: NaN everything greater than maximum, maximum should be constant
 category:Transformational
 definition:left_tail(x, maximum = 0)
 name: trade_when
 description: Used in order to change Alpha values only under a specified condition and to hold Alpha values in other cases. It also allows to close Alpha positions (assign NaN values) under a specified condition
 category:Transformational
 definition:trade_when(x, y, z)
 name: right_tail
 description: NaN everything less than minimum, minimum should be constant
 category:Transformational
 definition:right_tail(x, minimum = 0)
 name: bucket
 description: Convert float values into indexes for user-specified buckets. Bucket is useful for creating group values, which can be passed to GROUP as input
 category:Transformational
 definition:bucket(rank(x), range="0, 1, 0.1" or buckets = "2,5,6,7,10")
 name: group_rank
 description: Each elements in a group is assigned the corresponding rank in this group
 category:Group
 definition:group_rank(x, group)
 name: group_cartesian_product
 description: Merge two groups into one group. If originally there are len_1 and len_2 group indices in g1 and g2, there will be len_1 * len_2 indices in the new group.
 category:Group
 definition:group_cartesian_product(g1, g2)
 name: group_backfill
 description: If a certain value for a certain date and instrument is NaN, from the set of same group instruments, calculate winsorized mean of all non-NaN values over last d days
 category:Group
 definition:group_backfill(x, group, d, std = 4.0)
 name: group_mean
 description: All elements in group equals to the mean
 category:Group
 definition:group_mean(x, weight, group)
 name: group_neutralize
 description: Neutralizes Alpha against groups. These groups can be subindustry, industry, sector, country or a constant
 category:Group
 definition:group_neutralize(x, group)
 name: group_normalize
 description: Normalizes input such that each group's absolute sum is 1
 category:Group
 definition:group_normalize(x, group, constantCheck=False, tolerance=0.01, scale=1)
 name: group_median
 description: All elements in group equals to the median value of the group.
 category:Group
 definition:group_median(x, group)
 name: group_scale
 description: Normalizes the values in a group to be between 0 and 1. (x - groupmin) / (groupmax - groupmin)
 category:Group
 definition:group_scale(x, group)
 name: group_zscore
 description: Calculates group Z-score - numerical measurement that describes a value's relationship to the mean of a group of values. Z-score is measured in terms of standard deviations from the mean. zscore = (data - mean) / stddev of x for each instrument within its group.Input: Value of 5 instruments of Group A: (100, 0, 50, 60, 25)Output: (1.57, -1.39, 0.09, 0.39, -0.65)
 category:Group
 definition:group_zscore(x, group)