{
  "file_info": {
    "file_path": "./projects_cleaned.csv",
    "total_rows": 355,
    "total_columns": 22,
    "memory_usage_mb": 0.3523597717285156,
    "total_cells": 7810
  },
  "structural_info": {
    "column_names": [
      "project_number",
      "project_en",
      "developer_number",
      "developer_en",
      "start_date",
      "end_date",
      "adoption_date",
      "prj_type_en",
      "project_value",
      "escrow_account_number",
      "project_status",
      "percent_completed",
      "inspection_date",
      "completion_date",
      "description_en",
      "area_en",
      "zone_en",
      "cnt_land",
      "cnt_building",
      "cnt_villa",
      "cnt_unit",
      "master_project_en"
    ],
    "dtypes": {
      "project_number": "object",
      "project_en": "object",
      "developer_number": "object",
      "developer_en": "object",
      "start_date": "object",
      "end_date": "object",
      "adoption_date": "object",
      "prj_type_en": "object",
      "project_value": "float64",
      "escrow_account_number": "object",
      "project_status": "object",
      "percent_completed": "float64",
      "inspection_date": "object",
      "completion_date": "object",
      "description_en": "object",
      "area_en": "object",
      "zone_en": "object",
      "cnt_land": "float64",
      "cnt_building": "float64",
      "cnt_villa": "float64",
      "cnt_unit": "float64",
      "master_project_en": "object"
    },
    "index_info": {
      "type": "<class 'pandas.core.indexes.range.RangeIndex'>",
      "is_unique": true,
      "has_duplicates": "False"
    }
  },
  "columns_analysis": {
    "project_number": {
      "dtype": "object",
      "non_null_count": 355,
      "null_count": 0,
      "null_percentage": 0.0,
      "unique_values": 354,
      "unique_percentage": 99.72,
      "categorical_info": {
        "most_frequent": "3593",
        "most_frequent_count": 2,
        "least_frequent": "4167",
        "least_frequent_count": 1,
        "top_5_values": {
          "3593": 2,
          "807": 1,
          "986": 1,
          "2895": 1,
          "4063": 1
        }
      },
      "string_length": {
        "min": 3,
        "max": 122,
        "mean": 5.121126760563381,
        "median": 4.0
      }
    },
    "project_en": {
      "dtype": "object",
      "non_null_count": 340,
      "null_count": 15,
      "null_percentage": 4.23,
      "unique_values": 339,
      "unique_percentage": 99.71,
      "categorical_info": {
        "most_frequent": "d villas",
        "most_frequent_count": 2,
        "least_frequent": "rockland square",
        "least_frequent_count": 1,
        "top_5_values": {
          "d villas": 2,
          "samana resorts": 1,
          "reef 996": 1,
          "marina place 1": 1,
          "paradise one": 1
        }
      },
      "string_length": {
        "min": 4,
        "max": 65,
        "mean": 18.66764705882353,
        "median": 16.0
      }
    },
    "developer_number": {
      "dtype": "object",
      "non_null_count": 341,
      "null_count": 14,
      "null_percentage": 3.94,
      "unique_values": 216,
      "unique_percentage": 63.34,
      "categorical_info": {
        "most_frequent": "1002",
        "most_frequent_count": 17,
        "least_frequent": "2233",
        "least_frequent_count": 1,
        "top_5_values": {
          "1002": 17,
          "1866": 10,
          "2035": 9,
          "1051": 7,
          "1598": 7
        }
      },
      "string_length": {
        "min": 1,
        "max": 13,
        "mean": 3.9237536656891496,
        "median": 4.0
      }
    },
    "developer_en": {
      "dtype": "object",
      "non_null_count": 341,
      "null_count": 14,
      "null_percentage": 3.94,
      "unique_values": 215,
      "unique_percentage": 63.05,
      "categorical_info": {
        "most_frequent": "azizi developments l.l.c",
        "most_frequent_count": 17,
        "least_frequent": "cds real estate development l.l.c",
        "least_frequent_count": 1,
        "top_5_values": {
          "azizi developments l.l.c": 17,
          "damac mry investment l.l.c": 10,
          "damac elite investment co. l.l.c": 9,
          "binghatti developers fze": 7,
          "samana signature real estate developments l.l.c": 7
        }
      },
      "string_length": {
        "min": 1,
        "max": 80,
        "mean": 33.88563049853372,
        "median": 34.0
      }
    },
    "start_date": {
      "dtype": "object",
      "non_null_count": 341,
      "null_count": 14,
      "null_percentage": 3.94,
      "unique_values": 91,
      "unique_percentage": 26.69,
      "categorical_info": {
        "most_frequent": "2025-06-01 00:00:00",
        "most_frequent_count": 29,
        "least_frequent": "2025-09-22 00:00:00",
        "least_frequent_count": 1,
        "top_5_values": {
          "2025-06-01 00:00:00": 29,
          "2025-08-01 00:00:00": 26,
          "2025-09-01 00:00:00": 26,
          "2025-10-01 00:00:00": 25,
          "2025-07-01 00:00:00": 22
        }
      },
      "string_length": {
        "min": 1,
        "max": 147,
        "mean": 19.21700879765396,
        "median": 19.0
      }
    },
    "end_date": {
      "dtype": "object",
      "non_null_count": 340,
      "null_count": 15,
      "null_percentage": 4.23,
      "unique_values": 145,
      "unique_percentage": 42.65,
      "categorical_info": {
        "most_frequent": "2028-12-31 00:00:00",
        "most_frequent_count": 27,
        "least_frequent": "2027-03-22 00:00:00",
        "least_frequent_count": 1,
        "top_5_values": {
          "2028-12-31 00:00:00": 27,
          "2028-06-30 00:00:00": 13,
          "2027-09-30 00:00:00": 12,
          "2027-12-31 00:00:00": 12,
          "2029-03-31 00:00:00": 11
        }
      },
      "string_length": {
        "min": 1,
        "max": 24,
        "mean": 18.86764705882353,
        "median": 19.0
      }
    },
    "adoption_date": {
      "dtype": "object",
      "non_null_count": 254,
      "null_count": 101,
      "null_percentage": 28.45,
      "unique_values": 247,
      "unique_percentage": 97.24,
      "categorical_info": {
        "most_frequent": "2025-05-12 09:10:22",
        "most_frequent_count": 4,
        "least_frequent": "2025-10-07 13:40:37",
        "least_frequent_count": 1,
        "top_5_values": {
          "2025-05-12 09:10:22": 4,
          "2025-05-02 10:08:15": 2,
          "2025-05-07 11:23:23": 2,
          "2025-04-03 00:00:00": 2,
          "2025-05-05 00:00:00": 2
        }
      },
      "string_length": {
        "min": 19,
        "max": 23,
        "mean": 19.015748031496063,
        "median": 19.0
      }
    },
    "prj_type_en": {
      "dtype": "object",
      "non_null_count": 337,
      "null_count": 18,
      "null_percentage": 5.07,
      "unique_values": 1,
      "unique_percentage": 0.3,
      "categorical_info": {
        "most_frequent": "normal",
        "most_frequent_count": 337,
        "least_frequent": "normal",
        "least_frequent_count": 337,
        "top_5_values": {
          "normal": 337
        }
      },
      "string_length": {
        "min": 6,
        "max": 6,
        "mean": 6.0,
        "median": 6.0
      }
    },
    "project_value": {
      "dtype": "float64",
      "non_null_count": 336,
      "null_count": 19,
      "null_percentage": 5.35,
      "unique_values": 241,
      "unique_percentage": 71.73,
      "statistics": {
        "mean": 194081395.3690476,
        "median": 79570929.5,
        "std": 350877262.29434377,
        "min": 1000000.0,
        "max": 3033696240.0,
        "q25": 39500000.0,
        "q75": 188019286.75,
        "skewness": 4.632742026266175,
        "kurtosis": 27.186612055159774
      },
      "outliers": {
        "count": 41,
        "percentage": 11.55
      }
    },
    "escrow_account_number": {
      "dtype": "object",
      "non_null_count": 266,
      "null_count": 89,
      "null_percentage": 25.07,
      "unique_values": 265,
      "unique_percentage": 99.62,
      "categorical_info": {
        "most_frequent": "14041024920004",
        "most_frequent_count": 2,
        "least_frequent": "0205902532504",
        "least_frequent_count": 1,
        "top_5_values": {
          "14041024920004": 2,
          "012802437844": 1,
          "0012405538002": 1,
          "001582146524301": 1,
          "0012315743002": 1
        }
      },
      "string_length": {
        "min": 8,
        "max": 22,
        "mean": 13.041353383458647,
        "median": 13.0
      }
    },
    "project_status": {
      "dtype": "object",
      "non_null_count": 337,
      "null_count": 18,
      "null_percentage": 5.07,
      "unique_values": 3,
      "unique_percentage": 0.89,
      "categorical_info": {
        "most_frequent": "active",
        "most_frequent_count": 250,
        "least_frequent": "cancelled",
        "least_frequent_count": 2,
        "top_5_values": {
          "active": 250,
          "pending": 85,
          "cancelled": 2
        }
      },
      "string_length": {
        "min": 6,
        "max": 9,
        "mean": 6.270029673590504,
        "median": 6.0
      }
    },
    "percent_completed": {
      "dtype": "float64",
      "non_null_count": 313,
      "null_count": 42,
      "null_percentage": 11.83,
      "unique_values": 52,
      "unique_percentage": 16.61,
      "statistics": {
        "mean": 1.9477635782747607,
        "median": 0.0,
        "std": 8.867299446255698,
        "min": 0.0,
        "max": 68.05,
        "q25": 0.0,
        "q75": 0.0,
        "skewness": 5.342075911424932,
        "kurtosis": 29.34031228392463
      },
      "outliers": {
        "count": 55,
        "percentage": 15.49
      }
    },
    "inspection_date": {
      "dtype": "object",
      "non_null_count": 314,
      "null_count": 41,
      "null_percentage": 11.55,
      "unique_values": 313,
      "unique_percentage": 99.68,
      "categorical_info": {
        "most_frequent": "2025-02-27 19:48:36",
        "most_frequent_count": 2,
        "least_frequent": "2024-10-16 13:10:52",
        "least_frequent_count": 1,
        "top_5_values": {
          "2025-02-27 19:48:36": 2,
          "2025-10-13 18:21:58": 1,
          "2019-05-16 12:18:08": 1,
          "2025-04-24 16:25:26": 1,
          "2024-04-03 15:20:25": 1
        }
      },
      "string_length": {
        "min": 19,
        "max": 47,
        "mean": 19.089171974522294,
        "median": 19.0
      }
    },
    "completion_date": {
      "dtype": "object",
      "non_null_count": 2,
      "null_count": 353,
      "null_percentage": 99.44,
      "unique_values": 2,
      "unique_percentage": 100.0,
      "categorical_info": {
        "most_frequent": "2011-05-30 00:00:00",
        "most_frequent_count": 1,
        "least_frequent": "co-working spaces and a kids club. facilities in the complex open to members of the public include a selection of fine dining outlets and retail units on the podium level",
        "least_frequent_count": 1,
        "top_5_values": {
          "2011-05-30 00:00:00": 1,
          "co-working spaces and a kids club. facilities in the complex open to members of the public include a selection of fine dining outlets and retail units on the podium level": 1
        }
      },
      "string_length": {
        "min": 19,
        "max": 170,
        "mean": 94.5,
        "median": 94.5
      }
    },
    "description_en": {
      "dtype": "object",
      "non_null_count": 337,
      "null_count": 18,
      "null_percentage": 5.07,
      "unique_values": 319,
      "unique_percentage": 94.66,
      "categorical_info": {
        "most_frequent": "project consists of g+3p+14 residential building located in dubai investment park second, dubai. the building is designed to have a concrete structure and block with internal and external finishes.",
        "most_frequent_count": 4,
        "least_frequent": "b+g+3p+17",
        "least_frequent_count": 1,
        "top_5_values": {
          "project consists of g+3p+14 residential building located in dubai investment park second, dubai. the building is designed to have a concrete structure and block with internal and external finishes.": 4,
          "g+2p+12+roof": 3,
          "project consists of g+2p+8 residential building located in dubai investment park second, dubai. the building is designed to have a concrete structure and block with internal and external finishes.": 3,
          "3b + ground + m + 3ba + 16 + r": 3,
          "g+4+roof": 2
        }
      },
      "string_length": {
        "min": 1,
        "max": 783,
        "mean": 92.31750741839762,
        "median": 46.0
      }
    },
    "area_en": {
      "dtype": "object",
      "non_null_count": 337,
      "null_count": 18,
      "null_percentage": 5.07,
      "unique_values": 54,
      "unique_percentage": 16.02,
      "categorical_info": {
        "most_frequent": "palm deira",
        "most_frequent_count": 46,
        "least_frequent": "al hebiah second",
        "least_frequent_count": 1,
        "top_5_values": {
          "palm deira": 46,
          "madinat al mataar": 26,
          "wadi al safa 5": 24,
          "wadi al safa 3": 24,
          "al barsha south fourth": 24
        }
      },
      "string_length": {
        "min": 6,
        "max": 130,
        "mean": 16.13946587537092,
        "median": 14.0
      }
    },
    "zone_en": {
      "dtype": "object",
      "non_null_count": 239,
      "null_count": 116,
      "null_percentage": 32.68,
      "unique_values": 8,
      "unique_percentage": 3.35,
      "categorical_info": {
        "most_frequent": "dubai development authority (dda)",
        "most_frequent_count": 98,
        "least_frequent": "which is described as follows:",
        "least_frequent_count": 1,
        "top_5_values": {
          "dubai development authority (dda)": 98,
          "trakhees": 83,
          "dubai municipality": 41,
          "dubai south": 11,
          "dubai silicon oasis authority": 3
        }
      },
      "string_length": {
        "min": 8,
        "max": 60,
        "mean": 20.824267782426777,
        "median": 18.0
      }
    },
    "cnt_land": {
      "dtype": "float64",
      "non_null_count": 332,
      "null_count": 23,
      "null_percentage": 6.48,
      "unique_values": 7,
      "unique_percentage": 2.11,
      "statistics": {
        "mean": 0.2921686746987952,
        "median": 0.0,
        "std": 1.714219576647455,
        "min": 0.0,
        "max": 24.0,
        "q25": 0.0,
        "q75": 0.0,
        "skewness": 10.820064131532215,
        "kurtosis": 131.26326033728665
      },
      "outliers": {
        "count": 44,
        "percentage": 12.39
      }
    },
    "cnt_building": {
      "dtype": "float64",
      "non_null_count": 332,
      "null_count": 23,
      "null_percentage": 6.48,
      "unique_values": 1,
      "unique_percentage": 0.3,
      "statistics": {
        "mean": 0.0,
        "median": 0.0,
        "std": 0.0,
        "min": 0.0,
        "max": 0.0,
        "q25": 0.0,
        "q75": 0.0,
        "skewness": 0.0,
        "kurtosis": 0.0
      },
      "outliers": {
        "count": 0,
        "percentage": 0.0
      }
    },
    "cnt_villa": {
      "dtype": "float64",
      "non_null_count": 332,
      "null_count": 23,
      "null_percentage": 6.48,
      "unique_values": 29,
      "unique_percentage": 8.73,
      "statistics": {
        "mean": 22.087349397590362,
        "median": 0.0,
        "std": 95.07676127394544,
        "min": 0.0,
        "max": 1121.0,
        "q25": 0.0,
        "q75": 0.0,
        "skewness": 6.655005677088903,
        "kurtosis": 59.90362806054476
      },
      "outliers": {
        "count": 31,
        "percentage": 8.73
      }
    },
    "cnt_unit": {
      "dtype": "float64",
      "non_null_count": 332,
      "null_count": 23,
      "null_percentage": 6.48,
      "unique_values": 191,
      "unique_percentage": 57.53,
      "statistics": {
        "mean": 234.24698795180723,
        "median": 116.0,
        "std": 445.42724575376207,
        "min": 0.0,
        "max": 4526.0,
        "q25": 47.0,
        "q75": 269.75,
        "skewness": 6.465435974535892,
        "kurtosis": 54.86574287118425
      },
      "outliers": {
        "count": 26,
        "percentage": 7.32
      }
    },
    "master_project_en": {
      "dtype": "object",
      "non_null_count": 2,
      "null_count": 353,
      "null_percentage": 99.44,
      "unique_values": 2,
      "unique_percentage": 100.0,
      "categorical_info": {
        "most_frequent": "maison elysee iii by pantheon",
        "most_frequent_count": 1,
        "least_frequent": "mohammed bin rashid al maktoum city -district one west - phase 2",
        "least_frequent_count": 1,
        "top_5_values": {
          "maison elysee iii by pantheon": 1,
          "mohammed bin rashid al maktoum city -district one west - phase 2": 1
        }
      },
      "string_length": {
        "min": 29,
        "max": 64,
        "mean": 46.5,
        "median": 46.5
      }
    }
  },
  "data_quality": {
    "total_missing_values": 1350,
    "missing_percentage": 17.29,
    "columns_with_missing": {
      "project_en": 15,
      "developer_number": 14,
      "developer_en": 14,
      "start_date": 14,
      "end_date": 15,
      "adoption_date": 101,
      "prj_type_en": 18,
      "project_value": 19,
      "escrow_account_number": 89,
      "project_status": 18,
      "percent_completed": 42,
      "inspection_date": 41,
      "completion_date": 353,
      "description_en": 18,
      "area_en": 18,
      "zone_en": 116,
      "cnt_land": 23,
      "cnt_building": 23,
      "cnt_villa": 23,
      "cnt_unit": 23,
      "master_project_en": 353
    },
    "missing_percentage_by_column": {
      "project_en": 4.23,
      "developer_number": 3.94,
      "developer_en": 3.94,
      "start_date": 3.94,
      "end_date": 4.23,
      "adoption_date": 28.45,
      "prj_type_en": 5.07,
      "project_value": 5.35,
      "escrow_account_number": 25.07,
      "project_status": 5.07,
      "percent_completed": 11.83,
      "inspection_date": 11.55,
      "completion_date": 99.44,
      "description_en": 5.07,
      "area_en": 5.07,
      "zone_en": 32.68,
      "cnt_land": 6.48,
      "cnt_building": 6.48,
      "cnt_villa": 6.48,
      "cnt_unit": 6.48,
      "master_project_en": 99.44
    },
    "duplicate_rows": 0,
    "duplicate_percentage": 0.0
  },
  "statistical_summary": {
    "numeric_columns_count": 6,
    "categorical_columns_count": 16,
    "datetime_columns_count": 0,
    "data_types_distribution": {
      "object": 16,
      "float64": 6
    },
    "potential_identifier_columns": []
  }
}