docs: fix typo for "population" in the GeminiTextGenerator.predict(..., output_schema={...}) sample notebook (#1748)

* docs: fix type in output_schema sample notebook

* Update bq_dataframes_llm_output_schema.ipynb

Author: tswast

notebooks/generative_ai/bq_dataframes_llm_output_schema.ipynb

@@ -361,7 +361,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "You can also get float or int values, for example, to get polulations in millions:"
+    "You can also get float or int values, for example, to get populations in millions:"
    ]
   },
   {
@@ -400,7 +400,7 @@
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>city</th>\n",
-       "      <th>polulation_million</th>\n",
+       "      <th>population_in_millions</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
@@ -425,7 +425,7 @@
        "</div>[3 rows x 2 columns in total]"
       ],
       "text/plain": [
-       "       city  polulation_million\n",
+       "       city  population_in_millions\n",
        "0   Seattle                0.75\n",
        "1  New York               19.68\n",
        "2  Shanghai               26.32\n",
@@ -439,8 +439,8 @@
     }
    ],
    "source": [
-    "result = gemini.predict(df, prompt=[\"what is the population in millions of\", df[\"city\"]], output_schema={\"polulation_million\": \"float64\"})\n",
-    "result[[\"city\", \"polulation_million\"]]"
+    "result = gemini.predict(df, prompt=[\"what is the population in millions of\", df[\"city\"]], output_schema={\"population_in_millions\": \"float64\"})\n",
+    "result[[\"city\", \"population_in_millions\"]]"
    ]
   },
   {
@@ -576,7 +576,7 @@
        "      <th></th>\n",
        "      <th>city</th>\n",
        "      <th>is_US_city</th>\n",
-       "      <th>polulation_in_millions</th>\n",
+       "      <th>population_in_millions</th>\n",
        "      <th>rainy_days_per_year</th>\n",
        "    </tr>\n",
        "  </thead>\n",
@@ -608,7 +608,7 @@
        "</div>[3 rows x 4 columns in total]"
       ],
       "text/plain": [
-       "       city  is_US_city  polulation_in_millions  rainy_days_per_year\n",
+       "       city  is_US_city  population_in_millions  rainy_days_per_year\n",
        "0   Seattle        True                    0.75                  152\n",
        "1  New York        True                     8.8                  121\n",
        "2  Shanghai       False                   26.32                  115\n",
@@ -622,8 +622,8 @@
     }
    ],
    "source": [
-    "result = gemini.predict(df, prompt=[df[\"city\"]], output_schema={\"is_US_city\": \"bool\", \"polulation_in_millions\": \"float64\", \"rainy_days_per_year\": \"int64\"})\n",
-    "result[[\"city\", \"is_US_city\", \"polulation_in_millions\", \"rainy_days_per_year\"]]"
+    "result = gemini.predict(df, prompt=[df[\"city\"]], output_schema={\"is_US_city\": \"bool\", \"population_in_millions\": \"float64\", \"rainy_days_per_year\": \"int64\"})\n",
+    "result[[\"city\", \"is_US_city\", \"population_in_millions\", \"rainy_days_per_year\"]]"
    ]
   },
   {
@@ -677,7 +677,7 @@
        "      <th></th>\n",
        "      <th>city</th>\n",
        "      <th>is_US_city</th>\n",
-       "      <th>polulation_in_millions</th>\n",
+       "      <th>population_in_millions</th>\n",
        "      <th>rainy_days_per_year</th>\n",
        "      <th>places_to_visit</th>\n",
        "      <th>gps_coordinates</th>\n",
@@ -717,7 +717,7 @@
        "</div>[3 rows x 6 columns in total]"
       ],
       "text/plain": [
-       "       city  is_US_city  polulation_in_millions  rainy_days_per_year  \\\n",
+       "       city  is_US_city  population_in_millions  rainy_days_per_year  \\\n",
        "0   Seattle        True                    0.74                  150   \n",
        "1  New York        True                     8.4                  121   \n",
        "2  Shanghai       False                   26.32                  115   \n",
@@ -741,8 +741,8 @@
     }
    ],
    "source": [
-    "result = gemini.predict(df, prompt=[df[\"city\"]], output_schema={\"is_US_city\": \"bool\", \"polulation_in_millions\": \"float64\", \"rainy_days_per_year\": \"int64\", \"places_to_visit\": \"array<string>\", \"gps_coordinates\": \"struct<latitude float64, longitude float64>\"})\n",
-    "result[[\"city\", \"is_US_city\", \"polulation_in_millions\", \"rainy_days_per_year\", \"places_to_visit\", \"gps_coordinates\"]]"
+    "result = gemini.predict(df, prompt=[df[\"city\"]], output_schema={\"is_US_city\": \"bool\", \"population_in_millions\": \"float64\", \"rainy_days_per_year\": \"int64\", \"places_to_visit\": \"array<string>\", \"gps_coordinates\": \"struct<latitude float64, longitude float64>\"})\n",
+    "result[[\"city\", \"is_US_city\", \"population_in_millions\", \"rainy_days_per_year\", \"places_to_visit\", \"gps_coordinates\"]]"
    ]
   }
  ],