Hi everyone. I am new to PyMC and I am using the 5.10.0 version of this library. In my project below, I want to apply a different lag parameter to each independent variable. Upon running this, I get the error TypeError: 'TensorVariable' object cannot be interpreted as an integer. The reproducible code is as follows.
## Create a simple MMM data
import pandas as pd
from random import randint
import numpy as np
import pytensor.tensor as tt
import pytensor as pt
import pymc as pm
import pymc.sampling.jax as pmjax
import arviz as az
# Generate date range
dates = pd.date_range(start="2021-01-01", end="2022-01-01")
data = {
"date": dates,
"gcm_direct_Impressions": [randint(10000, 20000) for _ in dates],
"display_direct_Impressions" :[randint(100000,150000) for _ in dates],
"tv_grps": [randint(30, 50) for _ in dates],
"tiktok_direct_Impressions": [randint(10000, 15000) for _ in dates],
"sell_out_quantity": [randint(150, 250) for _ in dates]
}
df = pd.DataFrame(data)
m = max(df['sell_out_quantity'].values)
print(f"Max sales Volume {m}")
channel_columns = [col for col in df.columns if 'Impressions' in col or 'grps' in col]
transform_variables = channel_columns
delay_channels = channel_columns
media_channels = channel_columns
target = 'sell_out_quantity'
### Transform each channel variable
data_transformed = df.copy()
numerical_encoder_dict = {}
for feature in transform_variables:
# Extracting the original values of the feature.
original = df[feature].values
# Calculating the maximum value of the feature.
max_value = original.max()
# Dividing each value in the feature by the maximum value.
transformed = original / max_value
# Storing the transformed data back into the 'data_transformed' DataFrame.
data_transformed[feature] = transformed
# Storing the maximum value used for scaling in the dictionary.
# This will be used for reversing the transformation if needed.
numerical_encoder_dict[feature] = max_value
def adstock_transform(x, rate,max_lag):
""" Apply adstock transformation with PyTensor.
:param x: PyTensor tensor, original data for the channel
:param rate: PyTensor tensor, decay rate of the adstock transformation
:param max_lag: int, maximum lag to consider for the adstock effect
:return: PyTensor tensor, transformed data
"""
# Creating a tensor to store transformed values
adstocked = tt.zeros_like(x)
for i in range(max_lag, x.shape[0]):
weights = tt.power(rate, tt.arange(max_lag + 1))
adstocked = tt.set_subtensor(adstocked[i], tt.dot(x[i-max_lag:i+1][::-1], weights))
return adstocked
### Create a model
response_mean = []
with pm.Model() as model_2:
# Looping through each channel in the list of delay channels.
for channel_name in delay_channels:
print(f"Delay Channels: Adding {channel_name}")
# Extracting the transformed data for the current channel.
x = data_transformed[channel_name].values
# Defining Bayesian priors for the adstock, gamma, and alpha parameters for the current channel.
adstock_param = pm.Beta(f"{channel_name}_adstock", 2, 2)
saturation_gamma = pm.Beta(f"{channel_name}_gamma", 2, 2)
saturation_alpha = pm.Gamma(f"{channel_name}_alpha", 3, 1)
rate = pm.Beta(f'{channel_name}_rate', alpha=1, beta=1)
lag = pm.DiscreteUniform(f"{channel_name}_lag",lower=0,upper=17)
transformed_X1 = adstock_transform(x,rate,max_lag=lag)
transformed_X2 = tt.zeros_like(x)
for i in range(1,len(x)):
transformed_X2 = tt.set_subtensor(transformed_X2[i],(transformed_X1[i]**saturation_alpha)/(transformed_X1[i]**saturation_alpha+saturation_gamma**saturation_alpha))
channel_b = pm.HalfNormal(f"{channel_name}_media_coef", sigma = m)
response_mean.append(transformed_X2 * channel_b)
intercept = pm.Normal("intercept",mu = np.mean(data_transformed[target].values), sigma = 3)
sigma = pm.HalfNormal("sigma", 4)
likelihood = pm.Normal("outcome", mu = intercept + sum(response_mean), sigma = sigma,
observed = data_transformed[target].values)
with model_2:
trace = pmjax.sample_numpyro_nuts(1000, tune=1000, target_accept=0.95)
trace_summary = az.summary(trace)
One solution that I thought of was to replace max_lag in adstock_transform to int(max_lag.eval()). It still gives me the same error. I also tried replacing x = data_transformed[channel_name].values with x = pm.ConstantData("data_{channel_name",data_transformed[channel_name].values) and that did not work either. Should I choose a different distribution for the lag parameter for the sampling to work? Thanks in advance!
