closes #520 (#621) dataset -> data

pymc-labs · Sep 10, 2024 · f9b310f · f9b310f
1 parent 0085a33
commit f9b310f
Show file tree

Hide file tree

Showing 14 changed files with 13 additions and 13 deletions.
diff --git a/models/budget_optimizer_model_1.nc → data/budget_optimizer_model.nc b/models/budget_optimizer_model_1.nc → data/budget_optimizer_model.nc
diff --git a/datasets/cdnow_transactions.csv → data/cdnow_transactions.csv b/datasets/cdnow_transactions.csv → data/cdnow_transactions.csv
diff --git a/datasets/clv_quickstart.csv → data/clv_quickstart.csv b/datasets/clv_quickstart.csv → data/clv_quickstart.csv
diff --git a/datasets/mmm_example.csv → data/mmm_example.csv b/datasets/mmm_example.csv → data/mmm_example.csv
diff --git a/docs/source/guide/benefits/model_deployment.ipynb b/docs/source/guide/benefits/model_deployment.ipynb
@@ -173,7 +173,7 @@
     }
    ],
    "source": [
-    "url = \"https://raw.githubusercontent.com/pymc-labs/pymc-marketing/main/datasets/mmm_example.csv\"\n",
+    "url = \"https://raw.githubusercontent.com/pymc-labs/pymc-marketing/main/data/mmm_example.csv\"\n",
     "df = pd.read_csv(url)\n",
     "\n",
     "columns_to_keep = [\n",

diff --git a/docs/source/index.md b/docs/source/index.md
@@ -104,7 +104,7 @@ import pandas as pd
 from pymc_marketing.mmm import DelayedSaturatedMMM
 
 
-data_url = "https://raw.githubusercontent.com/pymc-labs/pymc-marketing/main/datasets/mmm_example.csv"
+data_url = "https://raw.githubusercontent.com/pymc-labs/pymc-marketing/main/data/mmm_example.csv"
 data = pd.read_csv(data_url, parse_dates=['date_week'])
 
 mmm = DelayedSaturatedMMM(
@@ -140,7 +140,7 @@ import seaborn as sns
 from pymc_marketing import clv
 
 
-data_url = "https://raw.githubusercontent.com/pymc-labs/pymc-marketing/main/datasets/clv_quickstart.csv"
+data_url = "https://raw.githubusercontent.com/pymc-labs/pymc-marketing/main/data/clv_quickstart.csv"
 data = pd.read_csv(data_url)
 data['customer_id'] = data.index
 

diff --git a/docs/source/notebooks/clv/bg_nbd.ipynb b/docs/source/notebooks/clv/bg_nbd.ipynb
@@ -143,7 +143,7 @@
     }
    ],
    "source": [
-    "data_path = \"https://raw.githubusercontent.com/pymc-labs/pymc-marketing/main/datasets/clv_quickstart.csv\"\n",
+    "data_path = \"https://raw.githubusercontent.com/pymc-labs/pymc-marketing/main/data/clv_quickstart.csv\"\n",
     "\n",
     "df = pd.read_csv(data_path)\n",
     "\n",

diff --git a/docs/source/notebooks/clv/clv_quickstart.ipynb b/docs/source/notebooks/clv/clv_quickstart.ipynb
@@ -167,7 +167,7 @@
     }
    ],
    "source": [
-    "raw_trans = pd.read_csv(\"https://raw.githubusercontent.com/pymc-labs/pymc-marketing/main/datasets/cdnow_transactions.csv\")\n",
+    "raw_trans = pd.read_csv(\"https://raw.githubusercontent.com/pymc-labs/pymc-marketing/main/data/cdnow_transactions.csv\")\n",
     "\n",
     "raw_trans.head(5)"
    ]

diff --git a/docs/source/notebooks/clv/dev/pareto_nbd.ipynb b/docs/source/notebooks/clv/dev/pareto_nbd.ipynb
@@ -89,7 +89,7 @@
     }
    ],
    "source": [
-    "url_cdnow_rfm = \"https://raw.githubusercontent.com/pymc-labs/pymc-marketing/main/datasets/clv_quickstart.csv\"\n",
+    "url_cdnow_rfm = \"https://raw.githubusercontent.com/pymc-labs/pymc-marketing/main/data/clv_quickstart.csv\"\n",
     "url_cdnow_trans = \"https://raw.githubusercontent.com/pymc-labs/pymc-marketing/main/tests/clv/datasets/cdnow_transactions.csv\"\n",
     "\n",
     "df = pd.read_csv(url_cdnow_rfm)\n",

diff --git a/docs/source/notebooks/clv/gamma_gamma.ipynb b/docs/source/notebooks/clv/gamma_gamma.ipynb
@@ -144,7 +144,7 @@
     }
    ],
    "source": [
-    "data_path = \"https://raw.githubusercontent.com/pymc-labs/pymc-marketing/main/datasets/clv_quickstart.csv\"\n",
+    "data_path = \"https://raw.githubusercontent.com/pymc-labs/pymc-marketing/main/data/clv_quickstart.csv\"\n",
     "\n",
     "summary_with_money_value = pd.read_csv(data_path)\n",
     "\n",

diff --git a/docs/source/notebooks/mmm/mmm_budget_allocation_example.ipynb b/docs/source/notebooks/mmm/mmm_budget_allocation_example.ipynb
@@ -119,7 +119,7 @@
    },
    "outputs": [],
    "source": [
-    "name = '/pymc-marketing/models/budget_optimizer_model_1.nc'\n",
+    "name = '/pymc-marketing/data/budget_optimizer_model.nc'\n",
     "mmm = DelayedSaturatedMMM.load(name)"
    ]
   },

diff --git a/pymc_marketing/mmm/delayed_saturated_mmm.py b/pymc_marketing/mmm/delayed_saturated_mmm.py
@@ -756,7 +756,7 @@ class DelayedSaturatedMMM(
 
         from pymc_marketing.mmm import DelayedSaturatedMMM
 
-        data_url = "https://raw.githubusercontent.com/pymc-labs/pymc-marketing/main/datasets/mmm_example.csv"
+        data_url = "https://raw.githubusercontent.com/pymc-labs/pymc-marketing/main/data/mmm_example.csv"
         data = pd.read_csv(data_url, parse_dates=["date_week"])
 
         mmm = DelayedSaturatedMMM(

diff --git a/tests/clv/models/test_pareto_nbd.py b/tests/clv/models/test_pareto_nbd.py
@@ -26,7 +26,7 @@ def setup_class(cls):
 
         # Use Quickstart dataset (the CDNOW_sample research data) for testing
         # TODO: Create a pytest fixture for this
-        test_data = pd.read_csv("datasets/clv_quickstart.csv")
+        test_data = pd.read_csv("data/clv_quickstart.csv")
         test_data["customer_id"] = test_data.index
 
         cls.data = test_data
@@ -358,7 +358,7 @@ def test_posterior_distributions(self, fit_type) -> None:
 
     def test_save_load_pareto_nbd(self):
         # TODO: Create a pytest fixture for this
-        test_data = pd.read_csv("datasets/clv_quickstart.csv")
+        test_data = pd.read_csv("data/clv_quickstart.csv")
         test_data["customer_id"] = test_data.index
         model = ParetoNBDModel(
             data=test_data,
@@ -394,7 +394,7 @@ def setup_class(cls):
             dropout_coefficient=np.array([3.0]),
         )
 
-        cls.data = data = pd.read_csv("datasets/clv_quickstart.csv").iloc[:500]
+        cls.data = data = pd.read_csv("data/clv_quickstart.csv").iloc[:500]
         data["customer_id"] = data.index
 
         # Create two purchase covariates and one dropout covariate

diff --git a/tests/conftest.py b/tests/conftest.py
@@ -49,7 +49,7 @@ def cdnow_trans() -> pd.DataFrame:
 
     Data source: https://www.brucehardie.com/datasets/
     """
-    return pd.read_csv("datasets/cdnow_transactions.csv")
+    return pd.read_csv("data/cdnow_transactions.csv")
 
 
 @pytest.fixture(scope="module")