Merge pull request #36 from MIT-Emerging-Talent/MLProject

Ml project

Author: MPKenley

.gitignore

@@ -1,6 +1,11 @@
 __pycache__
 *.pytest_cache
+<<<<<<< HEAD
+.venv/
+
+=======
 .env/
+>>>>>>> origin/main
 # .env
 *.db
 *.idea

.ls-lint.yml

@@ -4,6 +4,9 @@ ls:
   .md: snake_case | regex:[0-9A-Z\-]+
   .txt: snake_case | kebab-case
   .yml: snake_case | kebab-case
+  .ipynb: snake_case
+  .csv: snake_case
+  .py: snake_case
 
   .:                       # Répertoires racine
     .*/:
@@ -15,13 +18,28 @@ ignore:
   - .git
   - .github
   - .vscode
-  - venv
   - .ruff_cache
   - .pytest_cache
   - __pycache__
+<<<<<<< HEAD
+  - .venv
+  - **/site-packages/**
+  - 1_datasets
+  - data
+  - dist
+  - build
+
+rules:
+  some_rule: "true"   # string entre guillemets
+ignore:
+  - ".venv/"
+
+description: "Check code formatting: true/false"
+=======
   - .ls-lint.yml
   - .markdownlint.yml
 
 
 rules:
   some_rule: "true"
+>>>>>>> origin/main

1_datasets/haiti_catalog_raw_data/1st dataset_draft.....xlsx

@@ -187,13 +187,13 @@
    ],
    "source": [
     "# Load dataset for inbound UN arrivals arrivals tourist in the world\n",
-    "df = pd.read_excel (\"UN_Tourism_inbound_arrivals_10_2025.xlsx\")\n",
+    "df = pd.read_excel(\"UN_Tourism_inbound_arrivals_10_2025.xlsx\")\n",
     "df.head()\n",
     "# Load dataset for inbound UN arrivals arrivals tourist by purpose in the world\n",
     "df_purpose = pd.read_excel(\"UN_Tourism_inbound_arrivals_by_purpose_10_2025.xlsx\")\n",
     "df_purpose.head()\n",
     "# Load dataset for inbound UN arrivals arrivals tourist  by transport in the world\n",
-    "df_transport = pd.read_excel (\"UN_Tourism_inbound_arrivals_by_transport_10_2025.xlsx\")\n",
+    "df_transport = pd.read_excel(\"UN_Tourism_inbound_arrivals_by_transport_10_2025.xlsx\")\n",
     "df_transport.head()\n",
     "# Load dataset for inbound expenditure by tourists in the world\n",
     "df_expenditure = pd.read_excel(\"UN_Tourism_inbound_expenditure_10_2025.xlsx\")\n",
@@ -386,7 +386,9 @@
     "df_haiti_by_transport = df_transport[(df_transport[\"reporter_area_label\"] == \"Haiti\")]\n",
     "df_haiti_by_transport.head()\n",
     "# Load the inbound expenditure by tourists in the world dataset to extract data only for Haiti\n",
-    "df_haiti_by_expenditure = df_expenditure[(df_expenditure[\"reporter_area_label\"] == \"Haiti\")]\n",
+    "df_haiti_by_expenditure = df_expenditure[\n",
+    "    (df_expenditure[\"reporter_area_label\"] == \"Haiti\")\n",
+    "]\n",
     "df_haiti_by_expenditure.head()"
    ]
   },
@@ -398,13 +400,19 @@
    "outputs": [],
    "source": [
     "# save the df_haiti in a csv file\n",
-    "df_haiti.to_csv (\"UN_tourism_inbound_Arrivals_haiti.csv\",index = False)\n",
+    "df_haiti.to_csv(\"UN_tourism_inbound_Arrivals_haiti.csv\", index=False)\n",
     "# save the df_haiti_by_purpose in a csv file\n",
-    "df_haiti_by_purpose.to_csv(\"UN_tourism_inbound_Arrivals_haiti_by_purpose.csv\", index= False)\n",
+    "df_haiti_by_purpose.to_csv(\n",
+    "    \"UN_tourism_inbound_Arrivals_haiti_by_purpose.csv\", index=False\n",
+    ")\n",
     "# save the df_haiti_by_transport in a csv file\n",
-    "df_haiti_by_transport.to_csv(\"UN_tourism_inbound_Arrivals_haiti_by_transport.csv\", index= False)\n",
+    "df_haiti_by_transport.to_csv(\n",
+    "    \"UN_tourism_inbound_Arrivals_haiti_by_transport.csv\", index=False\n",
+    ")\n",
     "# save the df_haiti_by_expenditure in a csv file\n",
-    "df_haiti_by_expenditure.to_csv(\"UN_tourism_inbound_Arrivals_haiti_by_expenditure.csv\", index= False)"
+    "df_haiti_by_expenditure.to_csv(\n",
+    "    \"UN_tourism_inbound_Arrivals_haiti_by_expenditure.csv\", index=False\n",
+    ")"
    ]
   },
   {
@@ -612,10 +620,10 @@
    ],
    "source": [
     "# df[\"reporter_area_label\"].unique()\n",
-    "#df_haiti_by_purpose[\"year\"].unique()\n",
-    "#df_haiti_by_purpose.isnull().sum()\n",
-    "#df_haiti_by_transport.isnull().sum()\n",
-    "#df_haiti_by_expenditure.isnull().sum()\n",
+    "# df_haiti_by_purpose[\"year\"].unique()\n",
+    "# df_haiti_by_purpose.isnull().sum()\n",
+    "# df_haiti_by_transport.isnull().sum()\n",
+    "# df_haiti_by_expenditure.isnull().sum()\n",
     "df_haiti_by_expenditure[\"year\"].unique()"
    ]
   },
@@ -628,15 +636,37 @@
    "source": [
     "# create a array with the names the caribbean country to extract data for the caribbean region\n",
     "caribbean_countries = [\n",
-    "    \"Antigua and Barbuda\", \"Bahamas\", \"Barbados\", \"Belize\",\n",
-    "    \"Cuba\", \"Dominica\", \"Dominican Republic\", \"Grenada\",\n",
-    "    \"Jamaica\", \"Saint Kitts and Nevis\",\"Saint Lucia\",\"Haiti\",\n",
-    "    \"Saint Vincent and the Grenadines\", \"Trinidad and Tobago\",\n",
-    "    \"Anguilla\", \"Bermuda\", \"British Virgin Islands\", \"Cayman Islands\",\n",
-    "    \"Montserrat\", \"Turks and Caicos Islands\", \"Guadeloupe\", \"Martinique\",\n",
-    "    \"Aruba\", \"Curaçao\", \"Sint Maarten (Dutch part)\", \"Bonaire\",\n",
-    "    \"Saba\", \"St. Eustatius\", \"Puerto Rico\", \"United States Virgin Islands\"\n",
-    "]\n"
+    "    \"Antigua and Barbuda\",\n",
+    "    \"Bahamas\",\n",
+    "    \"Barbados\",\n",
+    "    \"Belize\",\n",
+    "    \"Cuba\",\n",
+    "    \"Dominica\",\n",
+    "    \"Dominican Republic\",\n",
+    "    \"Grenada\",\n",
+    "    \"Jamaica\",\n",
+    "    \"Saint Kitts and Nevis\",\n",
+    "    \"Saint Lucia\",\n",
+    "    \"Haiti\",\n",
+    "    \"Saint Vincent and the Grenadines\",\n",
+    "    \"Trinidad and Tobago\",\n",
+    "    \"Anguilla\",\n",
+    "    \"Bermuda\",\n",
+    "    \"British Virgin Islands\",\n",
+    "    \"Cayman Islands\",\n",
+    "    \"Montserrat\",\n",
+    "    \"Turks and Caicos Islands\",\n",
+    "    \"Guadeloupe\",\n",
+    "    \"Martinique\",\n",
+    "    \"Aruba\",\n",
+    "    \"Curaçao\",\n",
+    "    \"Sint Maarten (Dutch part)\",\n",
+    "    \"Bonaire\",\n",
+    "    \"Saba\",\n",
+    "    \"St. Eustatius\",\n",
+    "    \"Puerto Rico\",\n",
+    "    \"United States Virgin Islands\",\n",
+    "]"
    ]
   },
   {
@@ -646,7 +676,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# filter the dataset to keep data only for the caribbean region \n",
+    "# filter the dataset to keep data only for the caribbean region\n",
     "df_caribbean = df[df[\"reporter_area_label\"].isin(caribbean_countries)]"
    ]
   },