| \n", " | date | \n", "year | \n", "month | \n", "dayofyear | \n", "t | \n", "influencer_spend | \n", "shipping_threshold | \n", "intercept | \n", "trend | \n", "cs | \n", "cc | \n", "seasonality | \n", "epsilon | \n", "y | \n", "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", "2019-04-01 | \n", "2019 | \n", "4 | \n", "91 | \n", "0 | \n", "0.918883 | \n", "25.0 | \n", "2.0 | \n", "0.778279 | \n", "-0.012893 | \n", "0.006446 | \n", "-0.003223 | \n", "-0.118826 | \n", "2.561363 | \n", "
| 1 | \n", "2019-04-08 | \n", "2019 | \n", "4 | \n", "98 | \n", "1 | \n", "0.230898 | \n", "25.0 | \n", "2.0 | \n", "0.795664 | \n", "0.225812 | \n", "-0.113642 | \n", "0.056085 | \n", "0.064977 | \n", "2.264874 | \n", "
| 2 | \n", "2019-04-15 | \n", "2019 | \n", "4 | \n", "105 | \n", "2 | \n", "0.254486 | \n", "25.0 | \n", "2.0 | \n", "0.812559 | \n", "0.451500 | \n", "-0.232087 | \n", "0.109706 | \n", "-0.020269 | \n", "1.998208 | \n", "
| 3 | \n", "2019-04-22 | \n", "2019 | \n", "4 | \n", "112 | \n", "3 | \n", "0.035995 | \n", "25.0 | \n", "2.0 | \n", "0.828993 | \n", "0.651162 | \n", "-0.347175 | \n", "0.151993 | \n", "0.400209 | \n", "1.701116 | \n", "
| 4 | \n", "2019-04-29 | \n", "2019 | \n", "4 | \n", "119 | \n", "4 | \n", "0.336013 | \n", "25.0 | \n", "2.0 | \n", "0.844997 | \n", "0.813290 | \n", "-0.457242 | \n", "0.178024 | \n", "0.057609 | \n", "2.003646 | \n", "
<xarray.Dataset> Size: 33MB\n",
"Dimensions: (chain: 4, draw: 1000, control: 2,\n",
" fourier_mode: 4, date: 127,\n",
" channel: 1)\n",
"Coordinates:\n",
" * chain (chain) int64 32B 0 1 2 3\n",
" * draw (draw) int64 8kB 0 1 2 ... 998 999\n",
" * control (control) <U18 144B 'shipping_th...\n",
" * fourier_mode (fourier_mode) <U5 80B 'sin_1' ....\n",
" * date (date) datetime64[ns] 1kB 2019-0...\n",
" * channel (channel) <U16 64B 'influencer_s...\n",
"Data variables:\n",
" intercept_contribution (chain, draw) float64 32kB 0.803...\n",
" adstock_alpha (chain, draw) float64 32kB 0.474...\n",
" saturation_lam (chain, draw) float64 32kB 4.096...\n",
" saturation_beta (chain, draw) float64 32kB 0.782...\n",
" gamma_control (chain, draw, control) float64 64kB ...\n",
" gamma_fourier (chain, draw, fourier_mode) float64 128kB ...\n",
" y_sigma (chain, draw) float64 32kB 0.068...\n",
" channel_contribution (chain, draw, date, channel) float64 4MB ...\n",
" total_media_contribution_original_scale (chain, draw) float64 32kB 190.3...\n",
" control_contribution (chain, draw, date, control) float64 8MB ...\n",
" fourier_contribution (chain, draw, date, fourier_mode) float64 16MB ...\n",
" yearly_seasonality_contribution (chain, draw, date) float64 4MB ...\n",
"Attributes:\n",
" created_at: 2025-10-27T10:29:49.678161+00:00\n",
" arviz_version: 0.22.0\n",
" inference_library: pymc\n",
" inference_library_version: 5.25.1\n",
" sampling_time: 15.281957149505615\n",
" tuning_steps: 1000\n",
" pymc_marketing_version: 0.17.0<xarray.Dataset> Size: 528kB\n",
"Dimensions: (chain: 4, draw: 1000)\n",
"Coordinates:\n",
" * chain (chain) int64 32B 0 1 2 3\n",
" * draw (draw) int64 8kB 0 1 2 3 4 5 ... 995 996 997 998 999\n",
"Data variables: (12/18)\n",
" index_in_trajectory (chain, draw) int64 32kB -32 23 -46 -59 ... -45 -8 -8\n",
" perf_counter_start (chain, draw) float64 32kB 1.547e+06 ... 1.547e+06\n",
" energy (chain, draw) float64 32kB -136.3 -134.9 ... -138.1\n",
" energy_error (chain, draw) float64 32kB 0.5431 ... -9.683e-05\n",
" step_size_bar (chain, draw) float64 32kB 0.04843 ... 0.04397\n",
" max_energy_error (chain, draw) float64 32kB 0.7827 2.718 ... -0.09356\n",
" ... ...\n",
" divergences (chain, draw) int64 32kB 0 0 0 0 0 0 ... 0 0 0 0 0 0\n",
" diverging (chain, draw) bool 4kB False False ... False False\n",
" n_steps (chain, draw) float64 32kB 127.0 63.0 ... 63.0 127.0\n",
" lp (chain, draw) float64 32kB 142.4 141.9 ... 144.6\n",
" tree_depth (chain, draw) int64 32kB 7 6 6 6 6 6 ... 6 7 6 6 6 7\n",
" reached_max_treedepth (chain, draw) bool 4kB False False ... False False\n",
"Attributes:\n",
" created_at: 2025-10-27T10:29:49.686194+00:00\n",
" arviz_version: 0.22.0\n",
" inference_library: pymc\n",
" inference_library_version: 5.25.1\n",
" sampling_time: 15.281957149505615\n",
" tuning_steps: 1000<xarray.Dataset> Size: 2kB\n",
"Dimensions: (date: 127)\n",
"Coordinates:\n",
" * date (date) datetime64[ns] 1kB 2019-04-01 2019-04-08 ... 2021-08-30\n",
"Data variables:\n",
" y (date) float64 1kB 0.0 0.0 0.0 0.0 0.0 0.0 ... 0.0 0.0 0.0 0.0 0.0\n",
"Attributes:\n",
" created_at: 2025-10-27T10:29:50.279640+00:00\n",
" arviz_version: 0.22.0\n",
" inference_library: pymc\n",
" inference_library_version: 5.25.1<xarray.Dataset> Size: 6kB\n",
"Dimensions: (channel: 1, date: 127, control: 2)\n",
"Coordinates:\n",
" * channel (channel) <U16 64B 'influencer_spend'\n",
" * date (date) datetime64[ns] 1kB 2019-04-01 ... 2021-08-30\n",
" * control (control) <U18 144B 'shipping_threshold' 't'\n",
"Data variables:\n",
" channel_scale (channel) float64 8B 0.9919\n",
" target_scale float64 8B 3.981\n",
" channel_data (date, channel) float64 1kB 0.9189 0.2309 ... 0.2797 0.2041\n",
" target_data (date) float64 1kB 0.0 0.0 0.0 0.0 0.0 ... 0.0 0.0 0.0 0.0\n",
" control_data (date, control) float64 2kB 25.0 0.0 25.0 ... 20.0 126.0\n",
" dayofyear (date) int32 508B 91 98 105 112 119 ... 214 221 228 235 242\n",
"Attributes:\n",
" created_at: 2025-10-27T10:29:50.282164+00:00\n",
" arviz_version: 0.22.0\n",
" inference_library: pymc\n",
" inference_library_version: 5.25.1<xarray.Dataset> Size: 13kB\n",
"Dimensions: (date: 127)\n",
"Coordinates:\n",
" * date (date) datetime64[ns] 1kB 2019-04-01 ... 2021-08-30\n",
"Data variables: (12/13)\n",
" year (date) int32 508B 2019 2019 2019 2019 ... 2021 2021 2021\n",
" month (date) int32 508B 4 4 4 4 4 5 5 5 5 ... 7 7 7 8 8 8 8 8\n",
" dayofyear (date) int32 508B 91 98 105 112 119 ... 221 228 235 242\n",
" t (date) int64 1kB 0 1 2 3 4 5 ... 121 122 123 124 125 126\n",
" influencer_spend (date) float64 1kB 0.9189 0.2309 ... 0.2797 0.2041\n",
" shipping_threshold (date) float64 1kB 25.0 25.0 25.0 ... 20.0 20.0 20.0\n",
" ... ...\n",
" trend (date) float64 1kB 0.7783 0.7957 0.8126 ... 1.779 1.783\n",
" cs (date) float64 1kB -0.01289 0.2258 ... -0.9747 -0.8932\n",
" cc (date) float64 1kB 0.006446 -0.1136 ... -0.623 -0.5246\n",
" seasonality (date) float64 1kB -0.003223 0.05608 ... -0.7988 -0.7089\n",
" epsilon (date) float64 1kB -0.1188 0.06498 ... -0.3317 -0.05244\n",
" y (date) float64 1kB 2.561 2.265 1.998 ... 2.734 2.607<xarray.Dataset> Size: 4MB\n",
"Dimensions: (chain: 4, draw: 1000, date: 127)\n",
"Coordinates:\n",
" * chain (chain) int64 32B 0 1 2 3\n",
" * draw (draw) int64 8kB 0 1 2 3 4 5 6 7 ... 993 994 995 996 997 998 999\n",
" * date (date) datetime64[ns] 1kB 2019-04-01 2019-04-08 ... 2021-08-30\n",
"Data variables:\n",
" y (chain, draw, date) float64 4MB 0.6217 0.4625 ... 0.6679 0.6904\n",
"Attributes:\n",
" created_at: 2025-10-27T10:29:50.277380+00:00\n",
" arviz_version: 0.22.0\n",
" inference_library: pymc\n",
" inference_library_version: 5.25.1<xarray.Dataset> Size: 3MB\n",
"Dimensions: (sample: 4000, sweep: 100, channel: 1)\n",
"Coordinates:\n",
" * sample (sample) int64 32kB 0 1 2 3 4 5 6 ... 3994 3995 3996 3997 3998 3999\n",
" * sweep (sweep) float64 800B 0.1 0.1192 0.1384 0.1576 ... 1.962 1.981 2.0\n",
" * channel (channel) <U16 64B 'influencer_spend'\n",
"Data variables:\n",
" x (sample, sweep, channel) float64 3MB 5.693 6.779 ... 69.68 70.02<xarray.Dataset> Size: 3MB\n",
"Dimensions: (sample: 4000, sweep: 100)\n",
"Coordinates:\n",
" * sample (sample) int64 32kB 0 1 2 3 4 5 6 ... 3994 3995 3996 3997 3998 3999\n",
" * sweep (sweep) float64 800B 0.1 0.1192 0.1384 0.1576 ... 1.962 1.981 2.0\n",
" channel <U16 64B 'influencer_spend'\n",
"Data variables:\n",
" x (sample, sweep) float64 3MB 5.693 6.779 7.861 ... 69.35 69.68 70.02