wqb/alpha_tools
2
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

++

Browse Source
This commit is contained in:
jack
2026-02-05 10:18:53 +08:00
parent 717f8c1747
commit e8a4b2d318
364 changed files with 453102 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backup_code/wqb-server2/untracked/APP/operaters.csv
+129
View File
@@ -0,0 +1,129 @@
name,category,description
add,Arithmetic,"Add all inputs (at least 2 inputs required). If filter = true, filter all input NaN to 0 before adding"
exp,Arithmetic,Natural exponential function: e^x
multiply,Arithmetic,Multiply all inputs. At least 2 inputs are required. Filter sets the NaN values to 1
sign,Arithmetic,if input = NaN; return NaN
subtract,Arithmetic,"x-y. If filter = true, filter all input NaN to 0 before subtracting"
pasteurize,Arithmetic,Set to NaN if x is INF or if the underlying instrument is not in the Alpha universe. This operator may help reduce outliers.
log,Arithmetic,Natural logarithm. For example: Log(high/low) uses natural logarithm of high/low ratio as stock weights.
purify,Arithmetic,"Clear infinities (+inf, -inf) by replacing with NaN"
arc_tan,Arithmetic,This operator does inverse tangent of input
max,Arithmetic,Maximum value of all inputs. At least 2 inputs are required
arc_sin,Arithmetic,If -1 <= x <= 1: arcsin(x); else NaN
to_nan,Arithmetic,Convert value to NaN or NaN to value if reverse=true
abs,Arithmetic,Absolute value of x
round_down,Arithmetic,Round input to greatest multiple of f less than input;
sigmoid,Arithmetic,Returns 1 / (1 + exp(-x))
divide,Arithmetic,x / y
min,Arithmetic,Minimum value of all inputs. At least 2 inputs are required
nan_mask,Arithmetic,"replace input with NAN if input's corresponding mask value or the second input here, is negative"
arc_cos,Arithmetic,If -1 <= x <= 1: arccos(x); else NaN
tanh,Arithmetic,Hyperbolic tangent of x
nan_out,Arithmetic,"If x < lower or x > upper return NaN, else return x. At least one of ""lower"", ""upper"" is required"
signed_power,Arithmetic,x raised to the power of y such that final result preserves sign of x
inverse,Arithmetic,1 / x
round,Arithmetic,Round input to closest integer.
sqrt,Arithmetic,Square root of x
s_log_1p,Arithmetic,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
reverse,Arithmetic, - x
replace,Arithmetic,Replace target values in input with destination values
log_diff,Arithmetic,Returns log(current value of input or x[t] ) - log(previous value of input or x[t-1])
power,Arithmetic,x ^ y
densify,Arithmetic,Converts a grouping field of many buckets into lesser number of only available buckets so as to make working with grouping fields computationally efficient
fraction,Arithmetic,This operator removes the whole number part and returns the remaining fraction part with sign
floor,Arithmetic,Nearest smaller integer
ceiling,Arithmetic,Nearest larger integer
or,Logical,Logical OR operator returns true if either or both inputs are true and returns false otherwise
and,Logical,"Logical AND operator, returns true if both operands are true and returns false otherwise"
not,Logical,"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)."
is_not_finite,Logical,If (input NAN or input == INF) return 1 else return 0
negate,Logical,The result is true if the converted operand is false; the result is false if the converted operand is true
is_nan,Logical,If (input == NaN) return 1 else return 0
is_not_nan,Logical,If (input != NaN) return 1 else return 0
less,Logical,"If input1 < input2 return true, else return false"
equal,Logical,Returns true if both inputs are same and returns false otherwise
greater,Logical,Logic comparison operators to compares two inputs
is_finite,Logical,"If (input NaN or input == INF) return 0, else return 1"
if_else,Logical,If input1 is true then return input2 else return input3.
not_equal,Logical,Returns true if both inputs are NOT the same and returns false otherwise
less_equal,Logical,"Returns true if input1 <= input2, return false otherwise"
greater_equal,Logical,"Returns true if input1 >= input2, return false otherwise"
ts_corr,Time Series,Returns correlation of x and y for the past d days
ts_zscore,Time Series,"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."
ts_returns,Time Series,Returns the relative change in the x value
ts_product,Time Series,Returns product of x for the past d days
ts_std_dev,Time Series,Returns standard deviation of x for the past d days
ts_triple_corr,Time Series,"Returns triple correlation of x, y, z for the past d days"
ts_backfill,Time Series,"Backfill is the process of replacing the NAN or 0 values by a meaningful value (i.e., a first non-NaN value)"
days_from_last_change,Time Series,Amount of days since last change of x
last_diff_value,Time Series,Returns last x value not equal to current x value from last d days
ts_scale,Time Series,"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"
ts_entropy,Time Series,"For each instrument, we collect values of input in the past d days and calculate the probability distribution then the information entropy via a histogram as a result"
ts_vector_neut,Time Series,"Returns x- ts_vector_proj(x,y,d)"
ts_percentage,Time Series,Returns percentile value of x for the past d days
ts_step,Time Series,Returns days' counter
ts_sum,Time Series,Sum values of x for the past d days.
ts_co_kurtosis,Time Series,Returns cokurtosis of y and x for the past d days
ts_partial_corr,Time Series,"Returns partial correlation of x, y, z for the past d days"
inst_tvr,Time Series,Total trading value / Total holding value in the past d days
ts_decay_exp_window,Time Series,Returns exponential decay of x with smoothing factor for the past d days
ts_av_diff,Time Series,"Returns x - tsmean(x, d), but deals with NaNs carefully. That is NaNs are ignored during mean computation"
ts_rank_gmean_amean_diff,Time Series,"Returns Geometric Mean of ts_rank(input,d) of all input - Arithmetic Mean of ts_rank(input,d) of all input. This is similar to rank_gmean_amean_diff operator but in time-series space"
ts_kurtosis,Time Series,Returns kurtosis of x for the last d days
ts_mean,Time Series,Returns average value of x for the past d days.
ts_min_max_diff,Time Series,"Returns x - f * (ts_min(x, d) + ts_max(x, d)). If not specified, by default f = 0.5"
ts_arg_max,Time Series,"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"
ts_max,Time Series,Returns max value of x for the past d days
ts_min_max_cps,Time Series,"Returns (ts_min(x, d) + ts_max(x, d)) - f * x. If not specified, by default f = 2"
ts_rank,Time Series,"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."
ts_ir,Time Series,"Return information ratio ts_mean(x, d) / ts_std_dev(x, d)"
ts_delay,Time Series,Returns x value d days ago
ts_theilsen,Time Series,Theil Sen slope estimator of inputs for the past n days.
hump_decay,Time Series,This operator helps to ignore the values that changed too little corresponding to previous ones
ts_weighted_decay,Time Series,"Instead of replacing today's value with yesterday's as in ts_decay(x, 1), it assigns weighted average of today's and yesterday's values with weight on today's value being k and yesterday's being (1-k)"
ts_quantile,Time Series,"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."
ts_min,Time Series,Returns min value of x for the past d days
ts_count_nans,Time Series,Returns the number of NaN values in x for the past d days
ts_covariance,Time Series,Returns covariance of y and x for the past d days
ts_co_skewness,Time Series,Returns coskewness of y and x for the past d days
ts_min_diff,Time Series,"Returns x - ts_min(x, d)"
ts_decay_linear,Time Series,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.
jump_decay,Time Series,If there is a huge jump in current data compare to previous one
ts_moment,Time Series,Returns K-th central moment of x for the past d days
ts_arg_min,Time Series,"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."
ts_regression,Time Series,Returns various parameters related to regression function
ts_skewness,Time Series,Return skewness of x for the past d days
ts_max_diff,Time Series,"Returns x - ts_max(x, d)"
kth_element,Time Series,Returns K-th value of input by looking through lookback days. This operator can be used to backfill missing data if k=1
hump,Time Series,Limits amount and magnitude of changes in input (thus reducing turnover)
ts_median,Time Series,Returns median value of x for the past d days
ts_delta,Time Series,"Returns x - ts_delay(x, d)"
ts_poly_regression,Time Series,"Returns y - Ey, where Ey = x + x^2 + ... + x^k over d days; k must be specified as a keyword argument"
ts_vector_proj,Time Series,Returns vector projection of x onto y in time-series space.
ts_target_tvr_decay,Time Series,"Tune ""ts_decay"" to have a turnover equal to a certain target, with optimization weight range between lambda_min, lambda_max"
ts_target_tvr_delta_limit,Time Series,"Tune ""ts_delta_limit"" to have a turnover equal to a certain target with optimization weight range between lambda_min, lambda_max. 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."
ts_target_tvr_hump,Time Series,"Tune ""hump"" to have a turnover equal to a certain target with optimization weight range between lambda_min, lambda_max."
ts_delta_limit,Time Series,"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."
winsorize,Cross Sectional,"Winsorizes x to make sure that all values in x are between the lower and upper limits, which are specified as multiple of std."
rank,Cross Sectional,"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"
regression_proj,Cross Sectional,Conducts the cross-sectional regression on the stocks with Y as target and X as the independent variable
vector_neut,Cross Sectional,"For given vectors x and y, it finds a new vector x* (output) such that x* is orthogonal to y"
regression_neut,Cross Sectional,Conducts the cross-sectional regression on the stocks with Y as target and X as the independent variable
zscore,Cross Sectional,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
scale_down,Cross Sectional,Scales all values in each day proportionately between 0 and 1 such that minimum value maps to 0 and maximum value maps to 1. Constant is the offset by which final result is subtracted
truncate,Cross Sectional,"Operator truncates all values of x to maxPercent. Here, maxPercent is in decimal notation"
scale,Cross Sectional,Scales input to booksize. We can also scale the long positions and short positions to separate scales by mentioning additional parameters to the operator
rank_by_side,Cross Sectional,Ranks positive and negative input separately and scale to book. For precise sorting use rate=0
normalize,Cross Sectional,"Calculates the mean value of all valid alpha values for a certain date, then subtracts that mean from each element"
generalized_rank,Cross Sectional,The idea is that difference between instrument values raised to the power of m is added to the rank of instrument with bigger value and subtracted from the rank of instrument with lesser value. More details in the notes at the end of page
one_side,Cross Sectional,"Shifts all instruments up or down so that the Alpha becomes long-only or short-only (if side = short), respectively."
rank_gmean_amean_diff,Cross Sectional,Operator returns difference of geometric mean and arithmetic mean of cross sectional rank of inputs
quantile,Cross Sectional,"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"
vector_proj,Cross Sectional,Returns vector projection of x onto y.
multi_regression,Cross Sectional,"Perform multivariable regression of multiple independent variables (x1,x2,...) on a dependent variable (y) across number of days.
If days = n (n >= 0), will include past n days in the regression. Setting days = 0 indicates that we're only using today (x1, x2, ...) to predict y.
If lag = m (m >= 0), will lag (x1, x2, ...) for m days for prediction.
Options for solver: ""SVD""(default), ""QR"", ""NORMAL"""
1 name category description
2 add Arithmetic Add all inputs (at least 2 inputs required). If filter = true, filter all input NaN to 0 before adding
3 exp Arithmetic Natural exponential function: e^x
4 multiply Arithmetic Multiply all inputs. At least 2 inputs are required. Filter sets the NaN values to 1
5 sign Arithmetic if input = NaN; return NaN
6 subtract Arithmetic x-y. If filter = true, filter all input NaN to 0 before subtracting
7 pasteurize Arithmetic Set to NaN if x is INF or if the underlying instrument is not in the Alpha universe. This operator may help reduce outliers.
8 log Arithmetic Natural logarithm. For example: Log(high/low) uses natural logarithm of high/low ratio as stock weights.
9 purify Arithmetic Clear infinities (+inf, -inf) by replacing with NaN
10 arc_tan Arithmetic This operator does inverse tangent of input
11 max Arithmetic Maximum value of all inputs. At least 2 inputs are required
12 arc_sin Arithmetic If -1 <= x <= 1: arcsin(x); else NaN
13 to_nan Arithmetic Convert value to NaN or NaN to value if reverse=true
14 abs Arithmetic Absolute value of x
15 round_down Arithmetic Round input to greatest multiple of f less than input;
16 sigmoid Arithmetic Returns 1 / (1 + exp(-x))
17 divide Arithmetic x / y
18 min Arithmetic Minimum value of all inputs. At least 2 inputs are required
19 nan_mask Arithmetic replace input with NAN if input's corresponding mask value or the second input here, is negative
20 arc_cos Arithmetic If -1 <= x <= 1: arccos(x); else NaN
21 tanh Arithmetic Hyperbolic tangent of x
22 nan_out Arithmetic If x < lower or x > upper return NaN, else return x. At least one of "lower", "upper" is required
23 signed_power Arithmetic x raised to the power of y such that final result preserves sign of x
24 inverse Arithmetic 1 / x
25 round Arithmetic Round input to closest integer.
26 sqrt Arithmetic Square root of x
27 s_log_1p Arithmetic 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
28 reverse Arithmetic - x
29 replace Arithmetic Replace target values in input with destination values
30 log_diff Arithmetic Returns log(current value of input or x[t] ) - log(previous value of input or x[t-1])
31 power Arithmetic x ^ y
32 densify Arithmetic Converts a grouping field of many buckets into lesser number of only available buckets so as to make working with grouping fields computationally efficient
33 fraction Arithmetic This operator removes the whole number part and returns the remaining fraction part with sign
34 floor Arithmetic Nearest smaller integer
35 ceiling Arithmetic Nearest larger integer
36 or Logical Logical OR operator returns true if either or both inputs are true and returns false otherwise
37 and Logical Logical AND operator, returns true if both operands are true and returns false otherwise
38 not Logical 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).
39 is_not_finite Logical If (input NAN or input == INF) return 1 else return 0
40 negate Logical The result is true if the converted operand is false; the result is false if the converted operand is true
41 is_nan Logical If (input == NaN) return 1 else return 0
42 is_not_nan Logical If (input != NaN) return 1 else return 0
43 less Logical If input1 < input2 return true, else return false
44 equal Logical Returns true if both inputs are same and returns false otherwise
45 greater Logical Logic comparison operators to compares two inputs
46 is_finite Logical If (input NaN or input == INF) return 0, else return 1
47 if_else Logical If input1 is true then return input2 else return input3.
48 not_equal Logical Returns true if both inputs are NOT the same and returns false otherwise
49 less_equal Logical Returns true if input1 <= input2, return false otherwise
50 greater_equal Logical Returns true if input1 >= input2, return false otherwise
51 ts_corr Time Series Returns correlation of x and y for the past d days
52 ts_zscore Time Series 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.
53 ts_returns Time Series Returns the relative change in the x value
54 ts_product Time Series Returns product of x for the past d days
55 ts_std_dev Time Series Returns standard deviation of x for the past d days
56 ts_triple_corr Time Series Returns triple correlation of x, y, z for the past d days
57 ts_backfill Time Series Backfill is the process of replacing the NAN or 0 values by a meaningful value (i.e., a first non-NaN value)
58 days_from_last_change Time Series Amount of days since last change of x
59 last_diff_value Time Series Returns last x value not equal to current x value from last d days
60 ts_scale Time Series 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
61 ts_entropy Time Series For each instrument, we collect values of input in the past d days and calculate the probability distribution then the information entropy via a histogram as a result
62 ts_vector_neut Time Series Returns x- ts_vector_proj(x,y,d)
63 ts_percentage Time Series Returns percentile value of x for the past d days
64 ts_step Time Series Returns days' counter
65 ts_sum Time Series Sum values of x for the past d days.
66 ts_co_kurtosis Time Series Returns cokurtosis of y and x for the past d days
67 ts_partial_corr Time Series Returns partial correlation of x, y, z for the past d days
68 inst_tvr Time Series Total trading value / Total holding value in the past d days
69 ts_decay_exp_window Time Series Returns exponential decay of x with smoothing factor for the past d days
70 ts_av_diff Time Series Returns x - tsmean(x, d), but deals with NaNs carefully. That is NaNs are ignored during mean computation
71 ts_rank_gmean_amean_diff Time Series Returns Geometric Mean of ts_rank(input,d) of all input - Arithmetic Mean of ts_rank(input,d) of all input. This is similar to rank_gmean_amean_diff operator but in time-series space
72 ts_kurtosis Time Series Returns kurtosis of x for the last d days
73 ts_mean Time Series Returns average value of x for the past d days.
74 ts_min_max_diff Time Series Returns x - f * (ts_min(x, d) + ts_max(x, d)). If not specified, by default f = 0.5
75 ts_arg_max Time Series 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
76 ts_max Time Series Returns max value of x for the past d days
77 ts_min_max_cps Time Series Returns (ts_min(x, d) + ts_max(x, d)) - f * x. If not specified, by default f = 2
78 ts_rank Time Series 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.
79 ts_ir Time Series Return information ratio ts_mean(x, d) / ts_std_dev(x, d)
80 ts_delay Time Series Returns x value d days ago
81 ts_theilsen Time Series Theil Sen slope estimator of inputs for the past n days.
82 hump_decay Time Series This operator helps to ignore the values that changed too little corresponding to previous ones
83 ts_weighted_decay Time Series Instead of replacing today's value with yesterday's as in ts_decay(x, 1), it assigns weighted average of today's and yesterday's values with weight on today's value being k and yesterday's being (1-k)
84 ts_quantile Time Series 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.
85 ts_min Time Series Returns min value of x for the past d days
86 ts_count_nans Time Series Returns the number of NaN values in x for the past d days
87 ts_covariance Time Series Returns covariance of y and x for the past d days
88 ts_co_skewness Time Series Returns coskewness of y and x for the past d days
89 ts_min_diff Time Series Returns x - ts_min(x, d)
90 ts_decay_linear Time Series 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.
91 jump_decay Time Series If there is a huge jump in current data compare to previous one
92 ts_moment Time Series Returns K-th central moment of x for the past d days
93 ts_arg_min Time Series 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.
94 ts_regression Time Series Returns various parameters related to regression function
95 ts_skewness Time Series Return skewness of x for the past d days
96 ts_max_diff Time Series Returns x - ts_max(x, d)
97 kth_element Time Series Returns K-th value of input by looking through lookback days. This operator can be used to backfill missing data if k=1
98 hump Time Series Limits amount and magnitude of changes in input (thus reducing turnover)
99 ts_median Time Series Returns median value of x for the past d days
100 ts_delta Time Series Returns x - ts_delay(x, d)
101 ts_poly_regression Time Series Returns y - Ey, where Ey = x + x^2 + ... + x^k over d days; k must be specified as a keyword argument
102 ts_vector_proj Time Series Returns vector projection of x onto y in time-series space.
103 ts_target_tvr_decay Time Series Tune "ts_decay" to have a turnover equal to a certain target, with optimization weight range between lambda_min, lambda_max
104 ts_target_tvr_delta_limit Time Series Tune "ts_delta_limit" to have a turnover equal to a certain target with optimization weight range between lambda_min, lambda_max. 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.
105 ts_target_tvr_hump Time Series Tune "hump" to have a turnover equal to a certain target with optimization weight range between lambda_min, lambda_max.
106 ts_delta_limit Time Series 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.
107 winsorize Cross Sectional Winsorizes x to make sure that all values in x are between the lower and upper limits, which are specified as multiple of std.
108 rank Cross Sectional 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
109 regression_proj Cross Sectional Conducts the cross-sectional regression on the stocks with Y as target and X as the independent variable
110 vector_neut Cross Sectional For given vectors x and y, it finds a new vector x* (output) such that x* is orthogonal to y
111 regression_neut Cross Sectional Conducts the cross-sectional regression on the stocks with Y as target and X as the independent variable
112 zscore Cross Sectional 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
113 scale_down Cross Sectional Scales all values in each day proportionately between 0 and 1 such that minimum value maps to 0 and maximum value maps to 1. Constant is the offset by which final result is subtracted
114 truncate Cross Sectional Operator truncates all values of x to maxPercent. Here, maxPercent is in decimal notation
115 scale Cross Sectional Scales input to booksize. We can also scale the long positions and short positions to separate scales by mentioning additional parameters to the operator
116 rank_by_side Cross Sectional Ranks positive and negative input separately and scale to book. For precise sorting use rate=0
117 normalize Cross Sectional Calculates the mean value of all valid alpha values for a certain date, then subtracts that mean from each element
118 generalized_rank Cross Sectional The idea is that difference between instrument values raised to the power of m is added to the rank of instrument with bigger value and subtracted from the rank of instrument with lesser value. More details in the notes at the end of page
119 one_side Cross Sectional Shifts all instruments up or down so that the Alpha becomes long-only or short-only (if side = short), respectively.
120 rank_gmean_amean_diff Cross Sectional Operator returns difference of geometric mean and arithmetic mean of cross sectional rank of inputs
121 quantile Cross Sectional 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
122 vector_proj Cross Sectional Returns vector projection of x onto y.
123 multi_regression Cross Sectional Perform multivariable regression of multiple independent variables (x1,x2,...) on a dependent variable (y) across number of days. If days = n (n >= 0), will include past n days in the regression. Setting days = 0 indicates that we're only using today (x1, x2, ...) to predict y. If lag = m (m >= 0), will lag (x1, x2, ...) for m days for prediction. Options for solver: "SVD"(default), "QR", "NORMAL"