Skip to content

Commit 353f404

Browse files
skytin1004skytin1004
committed
chore(i18n): sync translations with latest source changes (chunk 10/10, 61 files)
1 parent 4abb311 commit 353f404

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

61 files changed

+14076
-0
lines changed

‎translations/te/6-NLP/4-Hotel-Reviews-1/solution/R/README.md‎

Lines changed: 17 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,17 @@
1+
<!--
2+
CO_OP_TRANSLATOR_METADATA:
3+
{
4+
"original_hash": "81db6ff2cf6e62fbe2340b094bb9509e",
5+
"translation_date": "2025-12-19T14:48:01+00:00",
6+
"source_file": "6-NLP/4-Hotel-Reviews-1/solution/R/README.md",
7+
"language_code": "te"
8+
}
9+
-->
10+
ఇది తాత్కాలిక ప్లేస్‌హోల్డర్‌입니다
11+
12+
---
13+
14+
<!-- CO-OP TRANSLATOR DISCLAIMER START -->
15+
**అస్పష్టత**:
16+
ఈ పత్రాన్ని AI అనువాద సేవ [Co-op Translator](https://github.com/Azure/co-op-translator) ఉపయోగించి అనువదించబడింది. మేము ఖచ్చితత్వానికి ప్రయత్నించినప్పటికీ, ఆటోమేటెడ్ అనువాదాల్లో పొరపాట్లు లేదా తప్పిదాలు ఉండవచ్చు. అసలు పత్రం దాని స్వదేశీ భాషలోనే అధికారిక మూలంగా పరిగణించాలి. ముఖ్యమైన సమాచారానికి, ప్రొఫెషనల్ మానవ అనువాదం సిఫార్సు చేయబడుతుంది. ఈ అనువాదం వాడకంలో ఏర్పడిన ఏవైనా అపార్థాలు లేదా తప్పుదారుల కోసం మేము బాధ్యత వహించము.
17+
<!-- CO-OP TRANSLATOR DISCLAIMER END -->

‎translations/te/6-NLP/4-Hotel-Reviews-1/solution/notebook.ipynb‎

Lines changed: 174 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,174 @@
1+
{
2+
"metadata": {
3+
"language_info": {
4+
"codemirror_mode": {
5+
"name": "ipython",
6+
"version": 3
7+
},
8+
"file_extension": ".py",
9+
"mimetype": "text/x-python",
10+
"name": "python",
11+
"nbconvert_exporter": "python",
12+
"pygments_lexer": "ipython3",
13+
"version": 3
14+
},
15+
"orig_nbformat": 4,
16+
"coopTranslator": {
17+
"original_hash": "2d05e7db439376aa824f4b387f8324ca",
18+
"translation_date": "2025-12-19T16:49:23+00:00",
19+
"source_file": "6-NLP/4-Hotel-Reviews-1/solution/notebook.ipynb",
20+
"language_code": "te"
21+
}
22+
},
23+
"nbformat": 4,
24+
"nbformat_minor": 2,
25+
"cells": [
26+
{
27+
"cell_type": "code",
28+
"execution_count": null,
29+
"metadata": {},
30+
"outputs": [],
31+
"source": [
32+
"# EDA\n",
33+
"import pandas as pd\n",
34+
"import time"
35+
]
36+
},
37+
{
38+
"cell_type": "code",
39+
"execution_count": null,
40+
"metadata": {},
41+
"outputs": [],
42+
"source": [
43+
"def get_difference_review_avg(row):\n",
44+
" return row[\"Average_Score\"] - row[\"Calc_Average_Score\"]"
45+
]
46+
},
47+
{
48+
"cell_type": "code",
49+
"execution_count": null,
50+
"metadata": {},
51+
"outputs": [],
52+
"source": [
53+
"# Load the hotel reviews from CSV\n",
54+
"print(\"Loading data file now, this could take a while depending on file size\")\n",
55+
"start = time.time()\n",
56+
"df = pd.read_csv('../../data/Hotel_Reviews.csv')\n",
57+
"end = time.time()\n",
58+
"print(\"Loading took \" + str(round(end - start, 2)) + \" seconds\")\n"
59+
]
60+
},
61+
{
62+
"cell_type": "code",
63+
"execution_count": null,
64+
"metadata": {},
65+
"outputs": [],
66+
"source": [
67+
"# What shape is the data (rows, columns)?\n",
68+
"print(\"The shape of the data (rows, cols) is \" + str(df.shape))\n"
69+
]
70+
},
71+
{
72+
"cell_type": "code",
73+
"execution_count": null,
74+
"metadata": {},
75+
"outputs": [],
76+
"source": [
77+
"# value_counts() creates a Series object that has index and values\n",
78+
"# in this case, the country and the frequency they occur in reviewer nationality\n",
79+
"nationality_freq = df[\"Reviewer_Nationality\"].value_counts()\n"
80+
]
81+
},
82+
{
83+
"cell_type": "code",
84+
"execution_count": null,
85+
"metadata": {},
86+
"outputs": [],
87+
"source": [
88+
"# What reviewer nationality is the most common in the dataset?\n",
89+
"print(\"The highest frequency reviewer nationality is \" + str(nationality_freq.index[0]).strip() + \" with \" + str(nationality_freq[0]) + \" reviews.\")\n"
90+
]
91+
},
92+
{
93+
"cell_type": "code",
94+
"execution_count": null,
95+
"metadata": {},
96+
"outputs": [],
97+
"source": [
98+
"# What is the top 10 most common nationalities and their frequencies?\n",
99+
"print(\"The top 10 highest frequency reviewer nationalities are:\")\n",
100+
"print(nationality_freq[0:10].to_string())\n"
101+
]
102+
},
103+
{
104+
"cell_type": "code",
105+
"execution_count": null,
106+
"metadata": {},
107+
"outputs": [],
108+
"source": [
109+
"# How many unique nationalities are there?\n",
110+
"print(\"There are \" + str(nationality_freq.index.size) + \" unique nationalities in the dataset\")\n"
111+
]
112+
},
113+
{
114+
"cell_type": "code",
115+
"execution_count": null,
116+
"metadata": {},
117+
"outputs": [],
118+
"source": [
119+
"# What was the most frequently reviewed hotel for the top 10 nationalities - print the hotel and number of reviews\n",
120+
"for nat in nationality_freq[:10].index:\n",
121+
" # First, extract all the rows that match the criteria into a new dataframe\n",
122+
" nat_df = df[df[\"Reviewer_Nationality\"] == nat] \n",
123+
" # Now get the hotel freq\n",
124+
" freq = nat_df[\"Hotel_Name\"].value_counts()\n",
125+
" print(\"The most reviewed hotel for \" + str(nat).strip() + \" was \" + str(freq.index[0]) + \" with \" + str(freq[0]) + \" reviews.\") \n"
126+
]
127+
},
128+
{
129+
"cell_type": "code",
130+
"execution_count": null,
131+
"metadata": {},
132+
"outputs": [],
133+
"source": [
134+
"# How many reviews are there per hotel (frequency count of hotel) and do the results match the value in `Total_Number_of_Reviews`?\n",
135+
"# First create a new dataframe based on the old one, removing the uneeded columns\n",
136+
"hotel_freq_df = df.drop([\"Hotel_Address\", \"Additional_Number_of_Scoring\", \"Review_Date\", \"Average_Score\", \"Reviewer_Nationality\", \"Negative_Review\", \"Review_Total_Negative_Word_Counts\", \"Positive_Review\", \"Review_Total_Positive_Word_Counts\", \"Total_Number_of_Reviews_Reviewer_Has_Given\", \"Reviewer_Score\", \"Tags\", \"days_since_review\", \"lat\", \"lng\"], axis = 1)\n",
137+
"# Group the rows by Hotel_Name, count them and put the result in a new column Total_Reviews_Found\n",
138+
"hotel_freq_df['Total_Reviews_Found'] = hotel_freq_df.groupby('Hotel_Name').transform('count')\n",
139+
"# Get rid of all the duplicated rows\n",
140+
"hotel_freq_df = hotel_freq_df.drop_duplicates(subset = [\"Hotel_Name\"])\n",
141+
"print()\n",
142+
"print(hotel_freq_df.to_string())\n",
143+
"print(str(hotel_freq_df.shape))"
144+
]
145+
},
146+
{
147+
"cell_type": "code",
148+
"execution_count": null,
149+
"metadata": {},
150+
"outputs": [],
151+
"source": [
152+
"# While there is an `Average_Score` for each hotel according to the dataset, \n",
153+
"# you can also calculate an average score (getting the average of all reviewer scores in the dataset for each hotel)\n",
154+
"# Add a new column to your dataframe with the column header `Calc_Average_Score` that contains that calculated average. \n",
155+
"df['Calc_Average_Score'] = round(df.groupby('Hotel_Name').Reviewer_Score.transform('mean'), 1)\n",
156+
"# Add a new column with the difference between the two average scores\n",
157+
"df[\"Average_Score_Difference\"] = df.apply(get_difference_review_avg, axis = 1)\n",
158+
"# Create a df without all the duplicates of Hotel_Name (so only 1 row per hotel)\n",
159+
"review_scores_df = df.drop_duplicates(subset = [\"Hotel_Name\"])\n",
160+
"# Sort the dataframe to find the lowest and highest average score difference\n",
161+
"review_scores_df = review_scores_df.sort_values(by=[\"Average_Score_Difference\"])\n",
162+
"print(review_scores_df[[\"Average_Score_Difference\", \"Average_Score\", \"Calc_Average_Score\", \"Hotel_Name\"]])\n",
163+
"# Do any hotels have the same (rounded to 1 decimal place) `Average_Score` and `Calc_Average_Score`?\n"
164+
]
165+
},
166+
{
167+
"cell_type": "markdown",
168+
"metadata": {},
169+
"source": [
170+
"---\n\n<!-- CO-OP TRANSLATOR DISCLAIMER START -->\n**అస్పష్టత**: \nఈ పత్రాన్ని AI అనువాద సేవ [Co-op Translator](https://github.com/Azure/co-op-translator) ఉపయోగించి అనువదించబడింది. మేము ఖచ్చితత్వానికి ప్రయత్నించినప్పటికీ, ఆటోమేటెడ్ అనువాదాల్లో పొరపాట్లు లేదా తప్పిదాలు ఉండవచ్చు. మూల పత్రం దాని స్వదేశీ భాషలోనే అధికారిక మూలంగా పరిగణించాలి. ముఖ్యమైన సమాచారానికి, ప్రొఫెషనల్ మానవ అనువాదం సిఫార్సు చేయబడుతుంది. ఈ అనువాదం వాడకం వల్ల కలిగే ఏవైనా అపార్థాలు లేదా తప్పుదారితీసే అర్థాలు కోసం మేము బాధ్యత వహించము.\n<!-- CO-OP TRANSLATOR DISCLAIMER END -->\n"
171+
]
172+
}
173+
]
174+
}

0 commit comments

Comments
 (0)