update datasets host url for notebooks (#959)

kgao · web-flow · commit da45e91aaa43 · 2025-03-28T02:04:06.000Z
Signed-off-by: kgao &lt;kevin.leo.gao@gmail.com&gt;
diff --git a/econml/tests/test_dominicks.py b/econml/tests/test_dominicks.py
@@ -19,7 +19,7 @@ def test_dominicks():
     if not os.path.isfile(file_name):
         print("Downloading file (this might take a few seconds)...")
         urllib.request.urlretrieve(
-            "https://msalicedatapublic.z5.web.core.windows.net/datasets/OrangeJuice/oj_large.csv", file_name)
+            "https://econmldata.azurewebsites.net/datasets/OrangeJuice/oj_large.csv", file_name)
     oj_data = pd.read_csv(file_name)
 
     brands = sorted(set(oj_data["brand"]))
diff --git a/notebooks/Causal Forest and Orthogonal Random Forest Examples.ipynb b/notebooks/Causal Forest and Orthogonal Random Forest Examples.ipynb
@@ -1514,7 +1514,7 @@
     "\n",
     "if not os.path.isfile(file_name):\n",
     "    print(\"Downloading file (this might take a few seconds)...\")\n",
-    "    urllib.request.urlretrieve(\"https://msalicedatapublic.z5.web.core.windows.net/datasets/OrangeJuice/oj_large.csv\",\n",
+    "    urllib.request.urlretrieve(\"https://econmldata.azurewebsites.net/datasets/OrangeJuice/oj_large.csv\",\n",
     "                               file_name)\n",
     "oj_data = pd.read_csv(file_name)\n",
     "oj_data.head()"
diff --git a/notebooks/CustomerScenarios/Case Study - Customer Segmentation at An Online Media Company - EconML + DoWhy.ipynb b/notebooks/CustomerScenarios/Case Study - Customer Segmentation at An Online Media Company - EconML + DoWhy.ipynb
@@ -136,7 +136,7 @@
    "outputs": [],
    "source": [
     "# Import the sample pricing data\n",
-    "file_url = \"https://msalicedatapublic.z5.web.core.windows.net/datasets/Pricing/pricing_sample.csv\"\n",
+    "file_url = \"https://econmldata.azurewebsites.net/datasets/Pricing/pricing_sample.csv\"\n",
     "train_data = pd.read_csv(file_url)"
    ]
   },
diff --git a/notebooks/CustomerScenarios/Case Study - Customer Segmentation at An Online Media Company.ipynb b/notebooks/CustomerScenarios/Case Study - Customer Segmentation at An Online Media Company.ipynb
@@ -122,7 +122,7 @@
    "outputs": [],
    "source": [
     "# Import the sample pricing data\n",
-    "file_url = \"https://msalicedatapublic.z5.web.core.windows.net/datasets/Pricing/pricing_sample.csv\"\n",
+    "file_url = \"https://econmldata.azurewebsites.net/datasets/Pricing/pricing_sample.csv\"\n",
     "train_data = pd.read_csv(file_url)"
    ]
   },
diff --git a/notebooks/CustomerScenarios/Case Study - Multi-investment Attribution at A Software Company - EconML + DoWhy.ipynb b/notebooks/CustomerScenarios/Case Study - Multi-investment Attribution at A Software Company - EconML + DoWhy.ipynb
@@ -125,7 +125,7 @@
    "outputs": [],
    "source": [
     "# Import the sample multi-attribution data\n",
-    "file_url = \"https://msalicedatapublic.z5.web.core.windows.net/datasets/ROI/multi_attribution_sample.csv\"\n",
+    "file_url = \"https://econmldata.azurewebsites.net/datasets/ROI/multi_attribution_sample.csv\"\n",
     "multi_data = pd.read_csv(file_url)"
    ]
   },
diff --git a/notebooks/CustomerScenarios/Case Study - Multi-investment Attribution at A Software Company.ipynb b/notebooks/CustomerScenarios/Case Study - Multi-investment Attribution at A Software Company.ipynb
@@ -108,7 +108,7 @@
    "outputs": [],
    "source": [
     "# Import the sample multi-attribution data\n",
-    "file_url = \"https://msalicedatapublic.z5.web.core.windows.net/datasets/ROI/multi_attribution_sample.csv\"\n",
+    "file_url = \"https://econmldata.azurewebsites.net/datasets/ROI/multi_attribution_sample.csv\"\n",
     "multi_data = pd.read_csv(file_url)"
    ]
   },
diff --git a/notebooks/CustomerScenarios/Case Study - Recommendation AB Testing at An Online Travel Company - EconML + DoWhy.ipynb b/notebooks/CustomerScenarios/Case Study - Recommendation AB Testing at An Online Travel Company - EconML + DoWhy.ipynb
@@ -145,7 +145,7 @@
    "outputs": [],
    "source": [
     "# Import the sample AB data\n",
-    "file_url = \"https://msalicedatapublic.z5.web.core.windows.net/datasets/RecommendationAB/ab_sample.csv\"\n",
+    "file_url = \"https://econmldata.azurewebsites.net/datasets/RecommendationAB/ab_sample.csv\"\n",
     "ab_data = pd.read_csv(file_url)"
    ]
   },
diff --git a/notebooks/CustomerScenarios/Case Study - Recommendation AB Testing at An Online Travel Company.ipynb b/notebooks/CustomerScenarios/Case Study - Recommendation AB Testing at An Online Travel Company.ipynb
@@ -133,7 +133,7 @@
    "outputs": [],
    "source": [
     "# Import the sample AB data\n",
-    "file_url = \"https://msalicedatapublic.z5.web.core.windows.net/datasets/RecommendationAB/ab_sample.csv\"\n",
+    "file_url = \"https://econmldata.azurewebsites.net/datasets/RecommendationAB/ab_sample.csv\"\n",
     "ab_data = pd.read_csv(file_url)"
    ]
   },
diff --git a/notebooks/CustomerScenarios/Case Study - Using EconML to evaluate the treatment effect of training program - Lalonde dataset.ipynb b/notebooks/CustomerScenarios/Case Study - Using EconML to evaluate the treatment effect of training program - Lalonde dataset.ipynb
@@ -337,7 +337,7 @@
     "# Data\n",
     "## female\n",
     "### read in and slice data\n",
-    "female_data = pd.read_csv('https://msalicedatapublic.z5.web.core.windows.net/datasets/Lalonde/calonico_smith_all.csv')\n",
+    "female_data = pd.read_csv('https://econmldata.azurewebsites.net/datasets/Lalonde/calonico_smith_all.csv')\n",
     "female_data[\"haschild\"]=(female_data[\"nchildren75\"]>0)*1\n",
     "female_data = female_data[pd.notnull(female_data.re75) & pd.notnull(female_data.re79)]\n",
     "female_treatment = female_data[female_data.treated==1.].copy()\n",
@@ -350,13 +350,13 @@
     "\n",
     "## male\n",
     "### read in and slice data\n",
-    "male_data = pd.read_csv('https://msalicedatapublic.z5.web.core.windows.net/datasets/Lalonde/smith_todd.csv')\n",
+    "male_data = pd.read_csv('https://econmldata.azurewebsites.net/datasets/Lalonde/smith_todd.csv')\n",
     "male_treatment = male_data[male_data.treated==1.].copy()\n",
     "male_control = male_data[male_data.treated==0.].copy()\n",
-    "male_cps1 = pd.read_csv('https://msalicedatapublic.z5.web.core.windows.net/datasets/Lalonde/cps_controls.csv')\n",
-    "male_psid1 = pd.read_csv('https://msalicedatapublic.z5.web.core.windows.net/datasets/Lalonde/psid_controls.csv')\n",
-    "male_cps3 = pd.read_csv('https://msalicedatapublic.z5.web.core.windows.net/datasets/Lalonde/cps_controls3.csv')\n",
-    "male_psid3 = pd.read_csv('https://msalicedatapublic.z5.web.core.windows.net/datasets/Lalonde/psid_controls3.csv')\n",
+    "male_cps1 = pd.read_csv('https://econmldata.azurewebsites.net/datasets/Lalonde/cps_controls.csv')\n",
+    "male_psid1 = pd.read_csv('https://econmldata.azurewebsites.net/datasets/Lalonde/psid_controls.csv')\n",
+    "male_cps3 = pd.read_csv('https://econmldata.azurewebsites.net/datasets/Lalonde/cps_controls3.csv')\n",
+    "male_psid3 = pd.read_csv('https://econmldata.azurewebsites.net/datasets/Lalonde/psid_controls3.csv')\n",
     "### some preprocessing\n",
     "for df in [male_psid1,male_psid3,male_cps1,male_cps3]:\n",
     "    df.rename(columns={'treat':'treated', 'education':'educ', 'hispanic':'hisp'}, inplace=True)"
diff --git a/notebooks/Double Machine Learning Examples.ipynb b/notebooks/Double Machine Learning Examples.ipynb
@@ -1923,7 +1923,7 @@
     "\n",
     "if not os.path.isfile(file_name):\n",
     "    print(\"Downloading file (this might take a few seconds)...\")\n",
-    "    urllib.request.urlretrieve(\"https://msalicedatapublic.z5.web.core.windows.net/datasets/OrangeJuice/oj_large.csv\",\n",
+    "    urllib.request.urlretrieve(\"https://econmldata.azurewebsites.net/datasets/OrangeJuice/oj_large.csv\",\n",
     "                               file_name)\n",
     "oj_data = pd.read_csv(file_name)"
    ]
diff --git a/notebooks/Solutions/Causal Interpretation for Employee Attrition Dataset.ipynb b/notebooks/Solutions/Causal Interpretation for Employee Attrition Dataset.ipynb
@@ -375,7 +375,7 @@
     }
    ],
    "source": [
-    "file_url = \"https://msalicedatapublic.z5.web.core.windows.net/datasets/EmployeeAttrition/Employee-Attrition.csv\"\n",
+    "file_url = \"https://econmldata.azurewebsites.net/datasets/EmployeeAttrition/Employee-Attrition.csv\"\n",
     "attritionData = pd.read_csv(file_url)\n",
     "attritionData.head(5)"
    ]

Original file line number	Diff line number	Diff line change
`@@ -136,7 +136,7 @@`
`136`	`136`	`"outputs": [],`
`137`	`137`	`"source": [`
`138`	`138`	`"# Import the sample pricing data\n",`
`139`		`- "file_url = \"https://msalicedatapublic.z5.web.core.windows.net/datasets/Pricing/pricing_sample.csv\"\n",`
	`139`	`+ "file_url = \"https://econmldata.azurewebsites.net/datasets/Pricing/pricing_sample.csv\"\n",`
`140`	`140`	`"train_data = pd.read_csv(file_url)"`
`141`	`141`	`]`
`142`	`142`	`},`
Original file line number	Diff line number	Diff line change
`@@ -122,7 +122,7 @@`
`122`	`122`	`"outputs": [],`
`123`	`123`	`"source": [`
`124`	`124`	`"# Import the sample pricing data\n",`
`125`		`- "file_url = \"https://msalicedatapublic.z5.web.core.windows.net/datasets/Pricing/pricing_sample.csv\"\n",`
	`125`	`+ "file_url = \"https://econmldata.azurewebsites.net/datasets/Pricing/pricing_sample.csv\"\n",`
`126`	`126`	`"train_data = pd.read_csv(file_url)"`
`127`	`127`	`]`
`128`	`128`	`},`
Original file line number	Diff line number	Diff line change
`@@ -125,7 +125,7 @@`
`125`	`125`	`"outputs": [],`
`126`	`126`	`"source": [`
`127`	`127`	`"# Import the sample multi-attribution data\n",`
`128`		`- "file_url = \"https://msalicedatapublic.z5.web.core.windows.net/datasets/ROI/multi_attribution_sample.csv\"\n",`
	`128`	`+ "file_url = \"https://econmldata.azurewebsites.net/datasets/ROI/multi_attribution_sample.csv\"\n",`
`129`	`129`	`"multi_data = pd.read_csv(file_url)"`
`130`	`130`	`]`
`131`	`131`	`},`
Original file line number	Diff line number	Diff line change
`@@ -108,7 +108,7 @@`
`108`	`108`	`"outputs": [],`
`109`	`109`	`"source": [`
`110`	`110`	`"# Import the sample multi-attribution data\n",`
`111`		`- "file_url = \"https://msalicedatapublic.z5.web.core.windows.net/datasets/ROI/multi_attribution_sample.csv\"\n",`
	`111`	`+ "file_url = \"https://econmldata.azurewebsites.net/datasets/ROI/multi_attribution_sample.csv\"\n",`
`112`	`112`	`"multi_data = pd.read_csv(file_url)"`
`113`	`113`	`]`
`114`	`114`	`},`
Original file line number	Diff line number	Diff line change
`@@ -145,7 +145,7 @@`
`145`	`145`	`"outputs": [],`
`146`	`146`	`"source": [`
`147`	`147`	`"# Import the sample AB data\n",`
`148`		`- "file_url = \"https://msalicedatapublic.z5.web.core.windows.net/datasets/RecommendationAB/ab_sample.csv\"\n",`
	`148`	`+ "file_url = \"https://econmldata.azurewebsites.net/datasets/RecommendationAB/ab_sample.csv\"\n",`
`149`	`149`	`"ab_data = pd.read_csv(file_url)"`
`150`	`150`	`]`
`151`	`151`	`},`
Original file line number	Diff line number	Diff line change
`@@ -133,7 +133,7 @@`
`133`	`133`	`"outputs": [],`
`134`	`134`	`"source": [`
`135`	`135`	`"# Import the sample AB data\n",`
`136`		`- "file_url = \"https://msalicedatapublic.z5.web.core.windows.net/datasets/RecommendationAB/ab_sample.csv\"\n",`
	`136`	`+ "file_url = \"https://econmldata.azurewebsites.net/datasets/RecommendationAB/ab_sample.csv\"\n",`
`137`	`137`	`"ab_data = pd.read_csv(file_url)"`
`138`	`138`	`]`
`139`	`139`	`},`
Original file line number	Diff line number	Diff line change
`@@ -1923,7 +1923,7 @@`
`1923`	`1923`	`"\n",`
`1924`	`1924`	`"if not os.path.isfile(file_name):\n",`
`1925`	`1925`	`" print(\"Downloading file (this might take a few seconds)...\")\n",`
`1926`		`- " urllib.request.urlretrieve(\"https://msalicedatapublic.z5.web.core.windows.net/datasets/OrangeJuice/oj_large.csv\",\n",`
	`1926`	`+ " urllib.request.urlretrieve(\"https://econmldata.azurewebsites.net/datasets/OrangeJuice/oj_large.csv\",\n",`
`1927`	`1927`	`" file_name)\n",`
`1928`	`1928`	`"oj_data = pd.read_csv(file_name)"`
`1929`	`1929`	`]`