MikeGreen2710/past_to_25_01_01_split_part_6_sanitized

--- dataset_info: features: - name: id dtype: int64 - name: title dtype: string - name: description dtype: string - name: address dtype: string - name: embed_text dtype: string - name: post_date_std dtype: timestamp[ns] - name: price_std dtype: float64 - name: source dtype: string - name: url dtype: string - name: agent_name dtype: string - name: agent_phone dtype: string - name: street_std dtype: string - name: door_direction_std dtype: string - name: number_of_floors_std dtype: float64 - name: house_front_std dtype: float64 - name: road_width_std dtype: float64 - name: total_wid_std dtype: float64 - name: total_len_std dtype: float64 - name: agri_area_std dtype: float64 - name: resi_area_std dtype: float64 - name: resi_cons_area_std dtype: float64 - name: total_area_std dtype: float64 - name: location dtype: int64 - name: project dtype: int64 - name: agriculture_forestry dtype: int64 - name: structure_focus dtype: int64 - name: province_code dtype: float64 - name: district_code dtype: float64 - name: ward_code dtype: float64 - name: matched_province dtype: string - name: matched_district dtype: string - name: matched_ward dtype: string - name: region dtype: string - name: province_ner dtype: string - name: district_ner dtype: string - name: ward_ner dtype: string - name: street_ner dtype: string - name: province_probability dtype: string - name: district_probability dtype: string - name: ward_probability dtype: string - name: street_probability dtype: string - name: province_score dtype: float64 - name: district_score dtype: float64 - name: ward_score dtype: float64 - name: location_probability dtype: float32 - name: project_probability dtype: float32 - name: agriculture_forestry_probability dtype: float32 - name: structure_focus_probability dtype: float32 - name: resolution_info dtype: string - name: resi_area_need_review dtype: bool - name: resi_cons_area_need_review dtype: bool - name: agri_area_need_review dtype: bool - name: text dtype: string splits: - name: train num_bytes: 6843125351 num_examples: 2000000 download_size: 3083174017 dataset_size: 6843125351 configs: - config_name: default data_files: - split: train path: data/train-* ---