dld_backend/rents_cleaned.json
2025-10-30 12:13:02 +05:30

602 lines
16 KiB
JSON

{
"file_info": {
"file_path": "./rents_cleaned.csv",
"total_rows": 4041,
"total_columns": 20,
"memory_usage_mb": 3.231393814086914,
"total_cells": 80820
},
"structural_info": {
"column_names": [
"registration_date",
"start_date",
"end_date",
"version_en",
"area_en",
"contract_amount",
"annual_amount",
"is_free_hold_en",
"actual_area",
"prop_type_en",
"prop_sub_type_en",
"rooms",
"usage_en",
"nearest_metro_en",
"nearest_mall_en",
"nearest_landmark_en",
"parking",
"total_properties",
"master_project_en",
"project_en"
],
"dtypes": {
"registration_date": "object",
"start_date": "object",
"end_date": "object",
"version_en": "object",
"area_en": "object",
"contract_amount": "float64",
"annual_amount": "float64",
"is_free_hold_en": "object",
"actual_area": "float64",
"prop_type_en": "object",
"prop_sub_type_en": "object",
"rooms": "float64",
"usage_en": "object",
"nearest_metro_en": "object",
"nearest_mall_en": "object",
"nearest_landmark_en": "object",
"parking": "float64",
"total_properties": "int64",
"master_project_en": "float64",
"project_en": "object"
},
"index_info": {
"type": "<class 'pandas.core.indexes.range.RangeIndex'>",
"is_unique": true,
"has_duplicates": "False"
}
},
"columns_analysis": {
"registration_date": {
"dtype": "object",
"non_null_count": 4041,
"null_count": 0,
"null_percentage": 0.0,
"unique_values": 3438,
"unique_percentage": 85.08,
"categorical_info": {
"most_frequent": "2025-10-20 13:06:58",
"most_frequent_count": 17,
"least_frequent": "2025-10-20 17:24:47",
"least_frequent_count": 1,
"top_5_values": {
"2025-10-20 13:06:58": 17,
"2025-10-20 12:37:18": 13,
"2025-10-20 13:04:34": 12,
"2025-10-20 12:52:09": 12,
"2025-10-20 16:03:53": 12
}
},
"string_length": {
"min": 19,
"max": 19,
"mean": 19.0,
"median": 19.0
}
},
"start_date": {
"dtype": "object",
"non_null_count": 4041,
"null_count": 0,
"null_percentage": 0.0,
"unique_values": 268,
"unique_percentage": 6.63,
"categorical_info": {
"most_frequent": "2025-10-20 00:00:00",
"most_frequent_count": 692,
"least_frequent": "2025-08-11 00:00:00",
"least_frequent_count": 1,
"top_5_values": {
"2025-10-20 00:00:00": 692,
"2025-11-01 00:00:00": 340,
"2025-10-15 00:00:00": 224,
"2025-10-01 00:00:00": 218,
"2025-10-25 00:00:00": 186
}
},
"string_length": {
"min": 19,
"max": 19,
"mean": 19.0,
"median": 19.0
}
},
"end_date": {
"dtype": "object",
"non_null_count": 4041,
"null_count": 0,
"null_percentage": 0.0,
"unique_values": 360,
"unique_percentage": 8.91,
"categorical_info": {
"most_frequent": "2026-10-19 00:00:00",
"most_frequent_count": 651,
"least_frequent": "2027-09-30 00:00:00",
"least_frequent_count": 1,
"top_5_values": {
"2026-10-19 00:00:00": 651,
"2026-10-31 00:00:00": 324,
"2026-10-14 00:00:00": 210,
"2026-09-30 00:00:00": 198,
"2026-10-24 00:00:00": 169
}
},
"string_length": {
"min": 19,
"max": 19,
"mean": 19.0,
"median": 19.0
}
},
"version_en": {
"dtype": "object",
"non_null_count": 4041,
"null_count": 0,
"null_percentage": 0.0,
"unique_values": 2,
"unique_percentage": 0.05,
"categorical_info": {
"most_frequent": "new",
"most_frequent_count": 2108,
"least_frequent": "renewed",
"least_frequent_count": 1933,
"top_5_values": {
"new": 2108,
"renewed": 1933
}
},
"string_length": {
"min": 3,
"max": 7,
"mean": 4.913387775303143,
"median": 3.0
}
},
"area_en": {
"dtype": "object",
"non_null_count": 4041,
"null_count": 0,
"null_percentage": 0.0,
"unique_values": 153,
"unique_percentage": 3.79,
"categorical_info": {
"most_frequent": "business bay",
"most_frequent_count": 241,
"least_frequent": "al warqa fourth",
"least_frequent_count": 1,
"top_5_values": {
"business bay": 241,
"burj khalifa": 157,
"al barsha south fourth": 148,
"al warsan first": 124,
"al khairan first": 119
}
},
"string_length": {
"min": 4,
"max": 33,
"mean": 14.49591685226429,
"median": 14.0
}
},
"contract_amount": {
"dtype": "float64",
"non_null_count": 4041,
"null_count": 0,
"null_percentage": 0.0,
"unique_values": 1021,
"unique_percentage": 25.27,
"statistics": {
"mean": 159085.6156570156,
"median": 68000.0,
"std": 616923.5558982035,
"min": 1500.0,
"max": 21419455.0,
"q25": 43890.0,
"q75": 120000.0,
"skewness": 19.31044630059915,
"kurtosis": 520.0640327240135
},
"outliers": {
"count": 403,
"percentage": 9.97
}
},
"annual_amount": {
"dtype": "float64",
"non_null_count": 4041,
"null_count": 0,
"null_percentage": 0.0,
"unique_values": 1032,
"unique_percentage": 25.54,
"statistics": {
"mean": 127422.4398020292,
"median": 68250.0,
"std": 285310.1898062665,
"min": 1000.0,
"max": 9058256.88,
"q25": 44850.0,
"q75": 120000.0,
"skewness": 12.831294216812893,
"kurtosis": 286.0873636060118
},
"outliers": {
"count": 389,
"percentage": 9.63
}
},
"is_free_hold_en": {
"dtype": "object",
"non_null_count": 4041,
"null_count": 0,
"null_percentage": 0.0,
"unique_values": 2,
"unique_percentage": 0.05,
"categorical_info": {
"most_frequent": "free hold",
"most_frequent_count": 2137,
"least_frequent": "non free hold",
"least_frequent_count": 1904,
"top_5_values": {
"free hold": 2137,
"non free hold": 1904
}
},
"string_length": {
"min": 9,
"max": 13,
"mean": 10.884682009403614,
"median": 9.0
}
},
"actual_area": {
"dtype": "float64",
"non_null_count": 4041,
"null_count": 0,
"null_percentage": 0.0,
"unique_values": 2000,
"unique_percentage": 49.49,
"statistics": {
"mean": 248.9395421925266,
"median": 77.0,
"std": 3441.055678528355,
"min": 1.0,
"max": 148698.0,
"q25": 44.77,
"q75": 118.86,
"skewness": 33.204341379662004,
"kurtosis": 1204.0698263128445
},
"outliers": {
"count": 323,
"percentage": 7.99
}
},
"prop_type_en": {
"dtype": "object",
"non_null_count": 4041,
"null_count": 0,
"null_percentage": 0.0,
"unique_values": 5,
"unique_percentage": 0.12,
"categorical_info": {
"most_frequent": "unit",
"most_frequent_count": 3607,
"least_frequent": "building",
"least_frequent_count": 2,
"top_5_values": {
"unit": 3607,
"villa": 295,
"virtual unit": 118,
"land": 19,
"building": 2
}
},
"string_length": {
"min": 4,
"max": 12,
"mean": 4.3085869834199455,
"median": 4.0
}
},
"prop_sub_type_en": {
"dtype": "object",
"non_null_count": 4022,
"null_count": 19,
"null_percentage": 0.47,
"unique_values": 21,
"unique_percentage": 0.52,
"categorical_info": {
"most_frequent": "flat",
"most_frequent_count": 2749,
"least_frequent": "workshop",
"least_frequent_count": 1,
"top_5_values": {
"flat": 2749,
"office": 559,
"villa": 280,
"shop": 261,
"labor camps": 57
}
},
"string_length": {
"min": 4,
"max": 17,
"mean": 4.592739930382894,
"median": 4.0
}
},
"rooms": {
"dtype": "float64",
"non_null_count": 166,
"null_count": 3875,
"null_percentage": 95.89,
"unique_values": 5,
"unique_percentage": 3.01,
"statistics": {
"mean": 3.2228915662650603,
"median": 3.0,
"std": 0.8833579597991758,
"min": 1.0,
"max": 5.0,
"q25": 3.0,
"q75": 4.0,
"skewness": -0.2396844059080121,
"kurtosis": 0.43579599092038057
},
"outliers": {
"count": 7,
"percentage": 0.17
}
},
"usage_en": {
"dtype": "object",
"non_null_count": 4021,
"null_count": 20,
"null_percentage": 0.49,
"unique_values": 4,
"unique_percentage": 0.1,
"categorical_info": {
"most_frequent": "residential",
"most_frequent_count": 3129,
"least_frequent": "educational facility",
"least_frequent_count": 1,
"top_5_values": {
"residential": 3129,
"commercial": 878,
"industrial": 13,
"educational facility": 1
}
},
"string_length": {
"min": 10,
"max": 20,
"mean": 10.780651579209152,
"median": 11.0
}
},
"nearest_metro_en": {
"dtype": "object",
"non_null_count": 3513,
"null_count": 528,
"null_percentage": 13.07,
"unique_values": 56,
"unique_percentage": 1.59,
"categorical_info": {
"most_frequent": "buj khalifa dubai mall metro station",
"most_frequent_count": 327,
"least_frequent": "energy metro station",
"least_frequent_count": 1,
"top_5_values": {
"buj khalifa dubai mall metro station": 327,
"rashidiya metro station": 302,
"dubai internet city": 214,
"business bay metro station": 191,
"creek metro station": 179
}
},
"string_length": {
"min": 9,
"max": 36,
"mean": 23.85681753487048,
"median": 23.0
}
},
"nearest_mall_en": {
"dtype": "object",
"non_null_count": 3384,
"null_count": 657,
"null_percentage": 16.26,
"unique_values": 5,
"unique_percentage": 0.15,
"categorical_info": {
"most_frequent": "dubai mall",
"most_frequent_count": 1420,
"least_frequent": "ibn-e-battuta mall",
"least_frequent_count": 193,
"top_5_values": {
"dubai mall": 1420,
"city centre mirdif": 969,
"mall of the emirates": 442,
"marina mall": 360,
"ibn-e-battuta mall": 193
}
},
"string_length": {
"min": 10,
"max": 20,
"mean": 14.159574468085106,
"median": 11.0
}
},
"nearest_landmark_en": {
"dtype": "object",
"non_null_count": 3691,
"null_count": 350,
"null_percentage": 8.66,
"unique_values": 13,
"unique_percentage": 0.35,
"categorical_info": {
"most_frequent": "dubai international airport",
"most_frequent_count": 1451,
"least_frequent": "hamdan sports complex",
"least_frequent_count": 3,
"top_5_values": {
"dubai international airport": 1451,
"downtown dubai": 491,
"burj khalifa": 463,
"sports city swimming academy": 392,
"burj al arab": 375
}
},
"string_length": {
"min": 10,
"max": 33,
"mean": 20.428339203467896,
"median": 27.0
}
},
"parking": {
"dtype": "float64",
"non_null_count": 106,
"null_count": 3935,
"null_percentage": 97.38,
"unique_values": 5,
"unique_percentage": 4.72,
"statistics": {
"mean": 0.8962264150943396,
"median": 1.0,
"std": 0.9554778937216891,
"min": 0.0,
"max": 4.0,
"q25": 0.0,
"q75": 2.0,
"skewness": 0.811920004167794,
"kurtosis": 0.2647111926218826
},
"outliers": {
"count": 0,
"percentage": 0.0
}
},
"total_properties": {
"dtype": "int64",
"non_null_count": 4041,
"null_count": 0,
"null_percentage": 0.0,
"unique_values": 15,
"unique_percentage": 0.37,
"statistics": {
"mean": 1.55456570155902,
"median": 1.0,
"std": 5.236775382015607,
"min": 1.0,
"max": 90.0,
"q25": 1.0,
"q75": 1.0,
"skewness": 13.298124808847174,
"kurtosis": 197.8723525800385
},
"outliers": {
"count": 155,
"percentage": 3.84
}
},
"master_project_en": {
"dtype": "float64",
"non_null_count": 0,
"null_count": 4041,
"null_percentage": 100.0,
"unique_values": 0,
"unique_percentage": 0,
"statistics": {
"mean": null,
"median": null,
"std": null,
"min": null,
"max": null,
"q25": null,
"q75": null,
"skewness": null,
"kurtosis": null
}
},
"project_en": {
"dtype": "object",
"non_null_count": 1289,
"null_count": 2752,
"null_percentage": 68.1,
"unique_values": 607,
"unique_percentage": 47.09,
"categorical_info": {
"most_frequent": "empire heights",
"most_frequent_count": 53,
"least_frequent": "pearls by vision",
"least_frequent_count": 1,
"top_5_values": {
"empire heights": 53,
"remraam": 14,
"remraam - al ramth": 14,
"remraam - al ramth 2": 14,
"the address dubai opera": 9
}
},
"string_length": {
"min": 2,
"max": 77,
"mean": 17.25833979829325,
"median": 15.0
}
}
},
"data_quality": {
"total_missing_values": 16177,
"missing_percentage": 20.02,
"columns_with_missing": {
"prop_sub_type_en": 19,
"rooms": 3875,
"usage_en": 20,
"nearest_metro_en": 528,
"nearest_mall_en": 657,
"nearest_landmark_en": 350,
"parking": 3935,
"master_project_en": 4041,
"project_en": 2752
},
"missing_percentage_by_column": {
"prop_sub_type_en": 0.47,
"rooms": 95.89,
"usage_en": 0.49,
"nearest_metro_en": 13.07,
"nearest_mall_en": 16.26,
"nearest_landmark_en": 8.66,
"parking": 97.38,
"master_project_en": 100.0,
"project_en": 68.1
},
"duplicate_rows": 0,
"duplicate_percentage": 0.0
},
"statistical_summary": {
"numeric_columns_count": 7,
"categorical_columns_count": 13,
"datetime_columns_count": 0,
"data_types_distribution": {
"object": 13,
"float64": 6,
"int64": 1
},
"potential_identifier_columns": []
}
}